© 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. 11-GEMMASCOPE-2-TRANSCODER-262K
    7. 35463
    Prev
    Next
    INDEX
    Explanations

    leading, advising, and administering 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_11_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
    raz
    0.54
    world
    0.46
     vlad
    0.46
    reg
    0.46
    bt
    0.45
    ፈል
    0.45
    渊
    0.44
    business
    0.44
    ments
    0.44
    watch
    0.43
    POSITIVE LOGITS
     Strauss
    0.54
     Patienten
    0.51
     його
    0.47
    Moses
    0.44
     রোগীর
    0.44
    و
    0.43
     መድሃኒ
    0.43
     রোগীদের
    0.42
     OPCODE
    0.42
     paziente
    0.42
    Activations Density 0.030%

    No Known Activations