© 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. 12-GEMMASCOPE-2-TRANSCODER-262K
    7. 199469
    Prev
    Next
    INDEX
    Explanations

    news agencies

    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_12_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
     dicho
    0.61
    cedent
    0.55
     "
    0.53
    сно
    0.53
    itively
    0.50
     opioid
    0.49
     drug
    0.49
    iziert
    0.49
     Node
    0.48
     복
    0.48
    POSITIVE LOGITS
    ’
    0.63
    לי
    0.50
    概要
    0.50
    ห
    0.50
    ریہ
    0.49
    ｈ
    0.49
    LV
    0.48
    뵈
    0.48
    𝟕
    0.48
    ων
    0.47
    Activations Density 0.000%

    No Known Activations