© 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. 31-GEMMASCOPE-2-TRANSCODER-262K
    7. 35594
    Prev
    Next
    INDEX
    Explanations

    crime reporting

    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_31_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
     simulators
    0.39
    [,,"
    0.38
     murdered
    0.36
    จัย
    0.34
     fuelwood
    0.34
    imeters
    0.34
    ~$
    0.33
     extinguished
    0.33
    "-"
    0.33
     mentors
    0.33
    POSITIVE LOGITS
     zis
    0.36
    쾅
    0.35
    toire
    0.34
    規
    0.34
    office
    0.33
     nz
    0.32
     эле
    0.32
     हाल
    0.32
    njih
    0.32
    派出
    0.32
    Activations Density 0.001%

    No Known Activations