© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 60-GEMMASCOPE-2-TRANSCODER-262K
    7. 90380
    Prev
    Next
    INDEX
    Explanations

    word problems

    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_60_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
    "..
    0.82
    Which
    0.74
    .."
    0.74
    ..
    0.69
     Which
    0.68
     WHICH
    0.67
    ..");
    0.67
    which
    0.66
    "
    0.63
    ..”
    0.62
    POSITIVE LOGITS
     how
    0.75
    ？
    0.68
     find
    0.66
     even
    0.64
     は
    0.60
     如何
    0.59
     даже
    0.57
    ?\\
    0.57
     cómo
    0.55
    )。
    0.54
    Activations Density 0.031%

    No Known Activations