© 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. 16-GEMMASCOPE-2-TRANSCODER-262K
    7. 217618
    Prev
    Next
    INDEX
    Explanations

    weirdness, free, dab, sun, packaging

    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_16_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
    0.53
     =
    0.53
     add
    0.49
     like
    0.48
    /*
    0.47
    完善
    0.47
    ll
    0.47
     adjust
    0.46
    I
    0.46
    rev
    0.46
    POSITIVE LOGITS
    ικό
    0.63
     게임
    0.52
    новения
    0.52
    ñón
    0.52
    ινή
    0.51
    𐰇
    0.49
    杲
    0.49
     filede
    0.48
    ڑوں
    0.48
    ዬ
    0.48
    Activations Density 0.000%

    No Known Activations