© 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. 9-GEMMASCOPE-2-TRANSCODER-262K
    7. 199113
    Prev
    Next
    INDEX
    Explanations

    account creation

    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_9_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
     Dash
    0.51
     B
    0.50
     M
    0.46
     Audit
    0.46
     Dark
    0.46
     Input
    0.46
     III
    0.45
     Image
    0.45
     문제를
    0.45
    }^{-}
    0.44
    POSITIVE LOGITS
    мани
    0.60
    мента
    0.59
    жуть
    0.57
    єднання
    0.52
     formulating
    0.49
     simulating
    0.48
    ли
    0.47
    ление
    0.47
    ியுள்ளது
    0.46
    からも
    0.46
    Activations Density 0.000%

    No Known Activations