© 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. 36211
    Prev
    Next
    INDEX
    Explanations

    zoophilia

    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
    at
    0.77
    А
    0.67
    ó
    0.66
    r
    0.61
    ë
    0.59
    .)
    0.59
    under
    0.59
    how
    0.58
    );
    0.57
     be
    0.56
    POSITIVE LOGITS
     napp
    0.73
    顗
    0.61
    ሮችን
    0.59
     dail
    0.58
     Wikiped
    0.58
     Muitos
    0.57
     rigidbody
    0.57
    cido
    0.56
     বাতিল
    0.55
    ეგისტრ
    0.55
    Activations Density 0.000%

    No Known Activations