© 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. 39827
    Prev
    Next
    INDEX
    Explanations

    serial killer

    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
     language
    0.60
     thờ
    0.58
    language
    0.55
     Oyster
    0.53
    ation
    0.52
    ون
    0.52
    ด
    0.51
    ed
    0.51
    aved
    0.49
    rą
    0.49
    POSITIVE LOGITS
    并购
    0.59
    NM
    0.55
     himself
    0.53
    NE
    0.53
    Liens
    0.53
    VOLUME
    0.53
    SEE
    0.52
    IDO
    0.52
     offend
    0.52
    Apex
    0.52
    Activations Density 0.003%

    No Known Activations