© 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. 55-GEMMASCOPE-2-TRANSCODER-262K
    7. 49428
    Prev
    Next
    INDEX
    Explanations

    URL

    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_55_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
     port
    0.42
     преда
    0.40
    袂
    0.39
     compuesto
    0.39
     maxLength
    0.37
     prototype
    0.36
     ою
    0.36
     presc
    0.36
    स्टेट
    0.36
    ણ
    0.35
    POSITIVE LOGITS
     http
    0.47
     https
    0.44
    (',');
    0.38
     절대
    0.38
     Pathways
    0.37
    <unused2165>
    0.37
     url
    0.37
     Supporting
    0.36
    Words
    0.36
    andia
    0.36
    Activations Density 0.001%

    No Known Activations