© 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-3-27B-IT
    5. 40-GEMMASCOPE-2-TRANSCODER-262K
    7. 28058
    Prev
    Next
    INDEX
    Explanations

    disclaimer text

    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_40_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
    pulumi
    0.38
    purecounter
    0.36
     límites
    0.35
    𝖗
    0.35
    чку
    0.35
     freak
    0.35
    usun
    0.35
    Thu
    0.35
    サン
    0.34
    တော့
    0.34
    POSITIVE LOGITS
     Tef
    0.44
    ﭜ
    0.43
    Inventory
    0.42
     یور
    0.41
    ایه
    0.40
    ayed
    0.37
     governing
    0.37
     العل
    0.36
    Stefan
    0.36
    Data
    0.36
    Activations Density 0.005%

    No Known Activations