© 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. 60-GEMMASCOPE-2-TRANSCODER-262K
    7. 155178
    Prev
    Next
    INDEX
    Explanations

    AI functions

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_60_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
     an
    0.69
     a
    0.66
     was
    0.60
     был
    0.60
     був
    0.58
     была
    0.57
    was
    0.56
    était
    0.55
     было
    0.51
     buvo
    0.51
    POSITIVE LOGITS
     that
    1.30
    that
    1.18
    That
    0.90
    ’
    0.90
    THAT
    0.82
    '
    0.79
     että
    0.78
     THAT
    0.77
     दैट
    0.72
     ότι
    0.69
    Activations Density 0.007%

    No Known Activations