© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-TRANSCODER-262K
    7. 163618
    Prev
    Next
    INDEX
    Explanations

    chains:

    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_31_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
    味道
    0.38
    occa
    0.35
     හො
    0.35
    AddModel
    0.35
    ッシング
    0.35
     insoluble
    0.34
    ostino
    0.34
    ⓶
    0.33
    ástico
    0.33
    ganos
    0.33
    POSITIVE LOGITS
     ABI
    0.39
    PlainText
    0.38
    上线
    0.38
     assemble
    0.38
     createTask
    0.37
     функциона
    0.37
     consul
    0.36
    コリ
    0.36
     項
    0.36
    痪
    0.35
    Activations Density 0.002%

    No Known Activations