© 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. 11-GEMMASCOPE-2-TRANSCODER-262K
    7. 61485
    Prev
    Next
    INDEX
    Explanations

    mapping out

    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_11_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
     गुणन
    0.19
    ων
    0.18
    戕
    0.18
    नैतिक
    0.18
     characterizing
    0.18
    endlich
    0.18
    сар
    0.18
     coercive
    0.18
    ק
    0.18
    inent
    0.17
    POSITIVE LOGITS
    ’
    0.25
    2
    0.21
    ({
    0.21
    Details
    0.20
    5
    0.20
    dH
    0.19
    {
    0.19
    0
    0.19
    sw
    0.19
    <table>
    0.18
    Activations Density 0.000%

    No Known Activations