© 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. 10-GEMMASCOPE-2-TRANSCODER-262K
    7. 24876
    Prev
    Next
    INDEX
    Explanations

    before and after chronological order

    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_10_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
     ۹
    0.83
    ９
    0.76
    9
    0.71
    h
    0.70
    ８
    0.70
     ۸
    0.68
    ۹
    0.68
    ICKEL
    0.65
    incorrect
    0.64
    Incorrect
    0.63
    POSITIVE LOGITS
     njih
    0.78
     थोड़ा
    0.72
     наличи
    0.70
     थोड़ा
    0.68
     //.
    0.68
    ியுடன்
    0.65
    ু
    0.65
     उनकी
    0.64
     presencia
    0.64
     اینکه
    0.64
    Activations Density 0.011%

    No Known Activations