© 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. 1-GEMMASCOPE-2-TRANSCODER-262K
    7. 134585
    Prev
    Next
    INDEX
    Explanations

    stator, gestator, destatis

    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_1_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
     to
    1.64
     been
    1.59
     be
    1.56
     from
    1.54
     are
    1.44
    0
    1.36
    ル
    1.32
     can
    1.30
    and
    1.30
    är
    1.28
    POSITIVE LOGITS
    ти
    1.37
    spiration
    0.98
    star
    0.92
    ᅱ
    0.91
    ших
    0.89
    ят
    0.88
    undance
    0.88
    д
    0.88
    nych
    0.86
    giveness
    0.84
    Activations Density 0.001%

    No Known Activations