© 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. 50-GEMMASCOPE-2-TRANSCODER-262K
    7. 175940
    Prev
    Next
    INDEX
    Explanations

    to

    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_50_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
    нні
    0.38
     Naz
    0.36
    idc
    0.35
     rö
    0.34
    igua
    0.34
    ツー
    0.34
    >]</
    0.33
    xsd
    0.32
    adf
    0.32
    chman
    0.32
    POSITIVE LOGITS
    handlungen
    0.45
    keiten
    0.44
    Staying
    0.43
     biting
    0.43
     Staying
    0.41
    ሖ
    0.41
    laying
    0.41
     lying
    0.41
    Constant
    0.40
    AGING
    0.39
    Activations Density 0.003%

    No Known Activations