© 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. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 86670
    Prev
    Next
    INDEX
    Explanations

    specific word endings or sequences

    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_3_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
    ing
    0.89
    uk
    0.86
    ä
    0.84
    ist
    0.82
    um
    0.80
    ie
    0.76
    ي
    0.76
    i
    0.72
    ig
    0.72
    ou
    0.71
    POSITIVE LOGITS
    ,
    0.77
    ו
    0.64
    StackTrace
    0.61
     bialgebras
    0.61
     सहारे
    0.58
     litros
    0.58
     as
    0.57
     наличи
    0.57
     skyrock
    0.57
    diagnostic
    0.57
    Activations Density 0.000%

    No Known Activations