© 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. 40-GEMMASCOPE-2-TRANSCODER-262K
    7. 16444
    Prev
    Next
    INDEX
    Explanations

    return statement or multiple choices

    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_40_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
     rownames
    0.33
    eventName
    0.32
    ⅜
    0.32
    Descripcion
    0.30
     DESCRIPTION
    0.30
     IAC
    0.29
     Thou
    0.29
     Description
    0.29
    AssetName
    0.29
    俱
    0.29
    POSITIVE LOGITS
    modern
    0.30
    Modern
    0.29
    Sets
    0.27
     modern
    0.27
     ken
    0.27
    erat
    0.27
    hile
    0.26
    standards
    0.26
    Pall
    0.26
     Sets
    0.26
    Activations Density 0.000%

    No Known Activations