© 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. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 86292
    Prev
    Next
    INDEX
    Explanations

    logarithm

    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_3_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
    </h3>
    0.76
    </blockquote>
    0.66
    দের
    0.66
    ก
    0.65
    ,
    0.65
    ).
    0.63
    ör
    0.63
    ),
    0.61
     defibr
    0.60
    ↵↵
    0.59
    POSITIVE LOGITS
    ہ
    0.82
    이었
    0.77
    امہ
    0.76
     интерес
    0.72
     وکړئ
    0.71
    <0x98>
    0.70
     sposob
    0.69
     aktivnosti
    0.69
    h
    0.68
    ޏ
    0.66
    Activations Density 0.001%

    No Known Activations