© 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. 53-GEMMASCOPE-2-TRANSCODER-262K
    7. 81615
    Prev
    Next
    INDEX
    Explanations

    can

    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_53_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
    asha
    0.46
    ◹
    0.43
    xa
    0.43
    𝘢
    0.42
    AuthConfig
    0.42
     chestnuts
    0.39
    Toolkit
    0.39
    取得
    0.39
    INTa
    0.39
    amel
    0.38
    POSITIVE LOGITS
     Compatible
    0.38
     Reagan
    0.37
     matchs
    0.36
     Persön
    0.35
     Гре
    0.35
     Demokrat
    0.35
     compatibles
    0.35
    蛋
    0.35
     Gre
    0.34
     ग्रे
    0.34
    Activations Density 0.002%

    No Known Activations