© 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. 2-GEMMASCOPE-2-TRANSCODER-262K
    7. 161908
    Prev
    Next
    INDEX
    Explanations

    code snippets/commands

    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_2_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
    ad
    1.27
    ar
    1.16
    د
    1.13
    い
    1.10
    te
    1.03
    ant
    0.99
    al
    0.98
    ER
    0.97
    ર
    0.97
    ts
    0.95
    POSITIVE LOGITS
    子の
    1.07
    ς
    1.02
    که
    0.99
    은
    0.94
    は
    0.91
    দের
    0.89
    汜
    0.88
    การ
    0.86
    ка
    0.86
    ה
    0.86
    Activations Density 0.001%

    No Known Activations