© 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. 216479
    Prev
    Next
    INDEX
    Explanations

    value

    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
    ulated
    0.42
    iciary
    0.39
    टीसी
    0.39
    ^{*}$.
    0.38
    Contours
    0.37
     BART
    0.35
     SMC
    0.35
     Mies
    0.35
    eling
    0.35
    浩
    0.35
    POSITIVE LOGITS
    ன்கள்
    0.46
    nan
    0.44
    蛜
    0.42
    NaN
    0.40
     actualmente
    0.39
    nju
    0.38
    attuale
    0.38
     Actualmente
    0.37
    ən
    0.37
     ਜਾਣ
    0.37
    Activations Density 0.000%

    No Known Activations