© 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. 13-GEMMASCOPE-2-TRANSCODER-262K
    7. 9572
    Prev
    Next
    INDEX
    Explanations

    brew and brewing

    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_13_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
     quizá
    0.21
    celebr
    0.21
    C
    0.21
    Fonte
    0.20
    Sumber
    0.20
     career
    0.20
     unrelated
    0.20
    Fuente
    0.19
    EK
    0.19
    financ
    0.19
    POSITIVE LOGITS
    òu
    0.22
    로는
    0.21
    直し
    0.20
     mae
    0.20
    стное
    0.20
    igheden
    0.19
    齙
    0.19
    <0xB6>
    0.19
     дета
    0.19
     DECIMAL
    0.19
    Activations Density 0.003%

    No Known Activations