© 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. 25-GEMMASCOPE-2-TRANSCODER-262K
    7. 241778
    Prev
    Next
    INDEX
    Explanations

    DataFrame column names

    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_25_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
     ponieważ
    0.41
     begrenzt
    0.40
    因为
    0.39
    При
    0.39
    unistd
    0.39
     dass
    0.38
     =
    0.38
    先日
    0.37
    Від
    0.37
    This
    0.36
    POSITIVE LOGITS
     పాటు
    0.40
     modes
    0.40
     collaborations
    0.40
    协作
    0.40
    effector
    0.39
     मायणी
    0.38
     families
    0.38
    탰
    0.38
     familias
    0.38
    টিয়ে
    0.38
    Activations Density 0.000%

    No Known Activations