© 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. 80149
    Prev
    Next
    INDEX
    Explanations

    sexual violence and domestic abuse

    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
    frac
    0.40
     Shooter
    0.39
    ạnh
    0.38
    ká
    0.38
     Macht
    0.37
    直
    0.37
     comport
    0.37
    ixas
    0.36
    nine
    0.36
     cuenta
    0.36
    POSITIVE LOGITS
    edal
    0.38
     diligence
    0.37
     Electrode
    0.37
    expandedTitle
    0.37
    يرين
    0.37
    沧
    0.36
    electrode
    0.36
     privé
    0.36
    嵘
    0.36
     diligently
    0.35
    Activations Density 0.003%

    No Known Activations