© 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. 22-GEMMASCOPE-2-TRANSCODER-262K
    7. 257793
    Prev
    Next
    INDEX
    Explanations

    difference betweenamountdifference between

    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_22_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
    zada
    0.41
     outflows
    0.41
     dije
    0.41
    qo
    0.40
     nivel
    0.40
     pile
    0.40
    <tfoot>
    0.39
    ᱗
    0.39
     tập
    0.39
     vực
    0.39
    POSITIVE LOGITS
    ങ്ങ്
    0.44
     शारीरिक
    0.43
    ឈ្ម
    0.42
     Neend
    0.40
    鼍
    0.40
     움
    0.39
     худож
    0.39
     लाख
    0.38
    ناة
    0.38
     mengembangkan
    0.38
    Activations Density 0.000%

    No Known Activations