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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-4B-IT
    5. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 8737
    Prev
    Next
    INDEX
    Explanations

    loop counters with punctuation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-4b-it/transcoder_all/layer_3_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
    ल
    2.36
    ں
    2.32
    to
    2.18
     zuten
    2.10
    ста
    2.07
    മ
    2.07
    ز
    2.02
    儡
    2.00
     што
    1.94
    penup
    1.94
    POSITIVE LOGITS
    ą
    2.66
     topological
    2.42
     vite
    2.32
     curbs
    2.24
     ureth
    2.24
     microtub
    2.22
     jurídico
    2.18
     worldly
    2.14
    于是
    2.14
     Fintech
    2.11
    Activations Density 0.044%

    No Known Activations