© 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. 6-GEMMASCOPE-2-TRANSCODER-262K
    7. 130070
    Prev
    Next
    INDEX
    Explanations

    common criteria

    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_6_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
     إ
    0.37
     œufs
    0.35
    াতিক
    0.34
     heeft
    0.33
    is
    0.32
    كه
    0.32
     את
    0.32
     će
    0.31
    كتب
    0.31
     ي
    0.31
    POSITIVE LOGITS
    lar
    0.46
    the
    0.43
    thed
    0.42
    g
    0.41
    rona
    0.37
    name
    0.36
    gul
    0.36
    tn
    0.35
    ओं
    0.35
    tum
    0.35
    Activations Density 0.001%

    No Known Activations