© 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. 56-GEMMASCOPE-2-TRANSCODER-262K
    7. 169955
    Prev
    Next
    INDEX
    Explanations

    let

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_56_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
    using
    0.53
     using
    0.52
     Using
    0.47
    Using
    0.47
    작
    0.44
    USING
    0.44
     allows
    0.42
    '),
    0.40
     '
    0.39
     (
    0.39
    POSITIVE LOGITS
     me
    0.68
     let
    0.50
    летка
    0.47
     Let
    0.47
    LETIN
    0.47
    LET
    0.45
     him
    0.44
     LET
    0.44
    letts
    0.44
    let
    0.43
    Activations Density 0.005%

    No Known Activations