© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 12-GEMMASCOPE-2-TRANSCODER-262K
    7. 201605
    Prev
    Next
    INDEX
    Explanations

    banking and financial transactions. Specifically, the neuron seems to be activated by terms related to money, payments, identity verification, and financial instruments like checks and PINs.Looking for common themes:- **PIN**: appears in MAX_ACTIVATING_TOKENS. Also seen in "PINs" in TOP_ACTIVATING_TEXTS.- **Checks/cheques**: appears multiple times. Seen in TOP_ACTIVATING_TEXTS related to "Returned Checks", "clearing of cheques", "paper check".- **Funds**: appears in MAX_ACTIVATING_TOKENS. Seen in "Non-Sufficient Funds" in TOP_ACTIVATING_TEXTS.PINs and checks

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_12_width_262k_l0_small_affine
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    дам
    0.41
    𝙎
    0.40
     bancos
    0.39
    Beverungen
    0.38
     बैंकिंग
    0.38
     banknotes
    0.38
    Banking
    0.38
     दत्त
    0.38
    钞
    0.37
    𝙋
    0.37
    POSITIVE LOGITS
     এল
    0.35
     R
    0.33
    ers
    0.33
    weight
    0.32
    )
    0.32
     El
    0.31
    og
    0.31
    expensive
    0.31
    <0x9D>
    0.31
    el
    0.30
    Activations Density 0.001%

    No Known Activations