© 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. 23811
    Prev
    Next
    INDEX
    Explanations

    `">`

    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
    TAG
    0.36
     muita
    0.35
    ປັນ
    0.34
    Dart
    0.32
    督
    0.32
     Macquarie
    0.32
    డు
    0.32
     Minds
    0.32
     Saka
    0.32
    ַ
    0.32
    POSITIVE LOGITS
     straight
    0.52
    //=
    0.47
    Straight
    0.45
    //
    0.45
    straight
    0.44
     Straight
    0.44
     strait
    0.44
    "'
    0.43
    //"
    0.41
    "(
    0.41
    Activations Density 0.002%

    No Known Activations