© 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. 176521
    Prev
    Next
    INDEX
    Explanations

    Pod

    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
    selector
    0.52
     selector
    0.43
    ilis
    0.42
    盟
    0.40
    isez
    0.40
    Selectors
    0.39
     gele
    0.39
    uler
    0.39
    ulis
    0.39
    onance
    0.38
    POSITIVE LOGITS
    титься
    0.42
    াফ
    0.39
    тился
    0.38
    чити
    0.38
    читься
    0.38
    гӀ
    0.36
    业
    0.36
     Uttar
    0.36
     рит
    0.36
    тить
    0.36
    Activations Density 0.000%

    No Known Activations