© 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. 49068
    Prev
    Next
    INDEX
    Explanations

    physical processes

    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
     hymn
    0.42
    jsko
    0.39
    ?—
    0.38
    covite
    0.37
    ⟋
    0.37
    .—
    0.36
     dren
    0.36
    claves
    0.36
    lüssel
    0.36
    yyyy
    0.36
    POSITIVE LOGITS
    ប
    0.42
    ';"
    0.39
     Interactions
    0.36
    Policies
    0.36
     Policies
    0.36
     المتع
    0.36
     Regions
    0.35
     ocasiones
    0.35
     তর
    0.35
     ព
    0.35
    Activations Density 0.020%

    No Known Activations