© 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. 42762
    Prev
    Next
    INDEX
    Explanations

    stylize (`--s`) parameter

    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
    矜
    0.34
    मुख
    0.30
     synergy
    0.30
     typescript
    0.29
     श्रृ
    0.29
     encapsulates
    0.29
     வெ
    0.29
    ക്കാല
    0.28
     configur
    0.28
    یکس
    0.28
    POSITIVE LOGITS
    ji
    0.37
    zahl
    0.33
    pta
    0.33
    萠
    0.31
    you
    0.31
    zhou
    0.31
    namefont
    0.31
    riert
    0.30
    zki
    0.29
    </th>
    0.29
    Activations Density 0.001%

    No Known Activations