© 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. 0-GEMMASCOPE-2-TRANSCODER-262K
    7. 83912
    Prev
    Next
    INDEX
    Explanations

    troll or trolling actions

    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_0_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
    ことにより
    1.28
    .
    1.17
    وی
    1.15
    Categorie
    1.09
    ем
    1.06
     exclu
    1.05
    ţin
    1.02
    šao
    1.02
    மாக
    1.01
    נה
    1.01
    POSITIVE LOGITS
    s
    3.20
    ع
    2.11
    p
    1.95
    g
    1.91
    ों
    1.86
    ur
    1.84
    y
    1.80
    h
    1.74
    u
    1.68
    ي
    1.63
    Activations Density 0.000%

    No Known Activations