© 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. 7-GEMMASCOPE-2-TRANSCODER-262K
    7. 35236
    Prev
    Next
    INDEX
    Explanations

    grid cell

    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_7_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
     as
    0.33
     by
    0.33
     has
    0.25
     is
    0.25
     when
    0.24
     be
    0.23
    c
    0.22
    st
    0.22
    ₃
    0.22
    ೨
    0.22
    POSITIVE LOGITS
    0.37
    ，
    0.30
    】，
    0.25
    ،
    0.24
    ।
    0.24
    <0xB3>
    0.23
    <0xA9>
    0.22
     vínculos
    0.22
    I
    0.22
    가가
    0.21
    Activations Density 0.003%

    No Known Activations