© 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. 56775
    Prev
    Next
    INDEX
    Explanations

    vibe

    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
    nies
    0.69
    !")
    0.65
     п
    0.63
    瓠
    0.61
    Photograph
    0.61
    skull
    0.60
     detract
    0.57
     papaya
    0.57
     ")"
    0.57
    Accessories
    0.57
    POSITIVE LOGITS
        
    0.57
    et
    0.57
    ↵
    0.55
    us
    0.55
    シ
    0.54
    em
    0.54
    ’
    0.54
    ah
    0.53
    </td>
    0.52
    ak
    0.51
    Activations Density 0.019%

    No Known Activations