© 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. 53649
    Prev
    Next
    INDEX
    Explanations

    utf-8 encoding

    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
     পছ
    0.44
    IfNeeded
    0.41
    ItemLayout
    0.39
    BERG
    0.38
     ಕೂದಲ
    0.38
    拵
    0.37
    SBOM
    0.37
    ))));
    0.36
     configs
    0.35
     wartime
    0.35
    POSITIVE LOGITS
     Titan
    0.41
    涩
    0.38
    Titan
    0.37
    ‪‬
    0.37
    …”
    0.37
    یکی
    0.36
    aphys
    0.36
    time
    0.36
    '){
    0.35
    ered
    0.35
    Activations Density 0.001%

    No Known Activations