© 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. 57-GEMMASCOPE-2-TRANSCODER-262K
    7. 39029
    Prev
    Next
    INDEX
    Explanations

    data formats

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_57_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
     siebie
    0.33
    돋
    0.32
     foam
    0.30
     diem
    0.30
     blaster
    0.30
     beamed
    0.29
    gyz
    0.28
     dope
    0.28
    রাষ্ট্রে
    0.28
     Wie
    0.27
    POSITIVE LOGITS
    <!
    0.35
    南
    0.31
    Chel
    0.31
    ।''
    0.30
    CHS
    0.29
     開始
    0.29
    Tara
    0.29
    Onset
    0.28
    angaroo
    0.28
     Tara
    0.28
    Activations Density 0.014%

    No Known Activations