© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 55-GEMMASCOPE-2-TRANSCODER-262K
    7. 51689
    Prev
    Next
    INDEX
    Explanations

    code

    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
    break
    0.44
    }];
    0.42
     "]";
    0.40
    _{-}\
    0.39
    ripple
    0.39
    subcategory
    0.38
    holds
    0.38
     QPushButton
    0.38
    鈮
    0.37
    retval
    0.36
    POSITIVE LOGITS
     Cover
    0.39
     Poverty
    0.39
     COVER
    0.39
    GYPT
    0.37
     diaper
    0.37
     Progress
    0.36
    ….
    0.36
     Resolve
    0.36
     Prada
    0.35
     Look
    0.35
    Activations Density 0.002%

    No Known Activations