© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 22-GEMMASCOPE-2-TRANSCODER-262K
    7. 261738
    Prev
    Next
    INDEX
    Explanations

    manuals or support

    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
     fuelled
    0.37
     ಸಾವ
    0.37
    谒
    0.37
    ionate
    0.36
     irrevers
    0.36
     crystals
    0.36
     hy
    0.36
     Wissenschaften
    0.35
     system
    0.35
     terminal
    0.35
    POSITIVE LOGITS
     જાણ
    0.47
    𒌅
    0.43
    फिर
    0.42
     পারিবারিক
    0.42
     Precio
    0.42
     یہی
    0.41
    ையினர்
    0.41
     Remington
    0.41
     Exempt
    0.40
    aujourd
    0.40
    Activations Density 0.001%

    No Known Activations