© 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. 46-GEMMASCOPE-2-TRANSCODER-262K
    7. 206286
    Prev
    Next
    INDEX
    Explanations

    government entities

    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_46_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
    Case
    0.47
    CTED
    0.46
     partida
    0.44
     Case
    0.43
    黨
    0.42
     case
    0.41
    パーティー
    0.41
     party
    0.40
    Creative
    0.40
    CASE
    0.39
    POSITIVE LOGITS
    mines
    0.39
    Luna
    0.39
     Luna
    0.38
     ...(
    0.38
     rhythmic
    0.37
    鳞
    0.37
    grid
    0.36
    minus
    0.36
     Tavern
    0.36
    YAN
    0.36
    Activations Density 0.010%

    No Known Activations