© 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. 31-GEMMASCOPE-2-TRANSCODER-262K
    7. 162313
    Prev
    Next
    INDEX
    Explanations

    number of times

    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_31_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
    鹭
    0.32
    issances
    0.32
     аст
    0.32
    тили
    0.32
    ʝ
    0.32
    Diff
    0.31
    千
    0.31
     nomad
    0.31
    坛
    0.31
    ᕕ
    0.31
    POSITIVE LOGITS
     ভারতবর্ষে
    0.39
     Caro
    0.38
     superfamily
    0.37
    inko
    0.37
     prolific
    0.36
     biosynthetic
    0.35
     Pharmaceutical
    0.34
    unek
    0.33
     antiseptic
    0.33
     cred
    0.33
    Activations Density 0.000%

    No Known Activations