© 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. 231536
    Prev
    Next
    INDEX
    Explanations

    fraud, ayuda, libros

    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
    <0x0D>
    0.67
     It
    0.63
    ’
    0.60
    -
    0.57
    .
    0.56
     r
    0.54
     j
    0.52
     for
    0.52
    $%
    0.52
     to
    0.51
    POSITIVE LOGITS
    g
    0.64
    và
    0.61
    thed
    0.57
     Neend
    0.56
    च्या
    0.56
     Schlüssel
    0.54
     KPK
    0.54
    ின்
    0.53
     extremadamente
    0.53
    gm
    0.53
    Activations Density 0.000%

    No Known Activations