© 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. 167063
    Prev
    Next
    INDEX
    Explanations

    Cosmopolitan sex advice, fashion contests

    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
    ራል
    0.42
     Theological
    0.36
     RULES
    0.36
    áját
    0.36
     mág
    0.35
     Invis
    0.35
    轱
    0.35
     Cheap
    0.35
    isDisabled
    0.35
     डॉक्यूमेंट्री
    0.35
    POSITIVE LOGITS
     contests
    0.42
     personality
    0.41
     contest
    0.40
    뽑
    0.39
     fashion
    0.38
     뽑
    0.38
     personalities
    0.38
     express
    0.37
    轿
    0.36
    流行
    0.35
    Activations Density 0.010%

    No Known Activations