© 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. 34-GEMMASCOPE-2-TRANSCODER-262K
    7. 17611
    Prev
    Next
    INDEX
    Explanations

    oral sex, kissing, licking

    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_34_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
     разби
    0.46
    ssid
    0.43
    विच
    0.40
    izarra
    0.40
     Разби
    0.39
    jog
    0.39
    gyro
    0.38
    策
    0.38
    upload
    0.38
    Operational
    0.38
    POSITIVE LOGITS
     biting
    0.52
     bites
    0.49
     snacking
    0.49
     bite
    0.49
    咬
    0.49
     nib
    0.47
     chom
    0.47
     attacc
    0.47
     Bites
    0.46
     teeth
    0.45
    Activations Density 0.095%

    No Known Activations