© 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. 35905
    Prev
    Next
    INDEX
    Explanations

    criminology or professional law

    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
     excès
    0.57
    Downtown
    0.50
    $};
    0.49
    يا
    0.49
    landı
    0.49
    “
    0.48
     তবে
    0.47
    أل
    0.47
    heartedly
    0.46
    “-
    0.46
    POSITIVE LOGITS
     memes
    0.46
     TPM
    0.45
     Haemat
    0.44
    嶌
    0.44
     interface
    0.44
     modelling
    0.44
     NEM
    0.43
     MED
    0.41
     моде
    0.41
     karne
    0.41
    Activations Density 0.000%

    No Known Activations