© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 46-GEMMASCOPE-2-TRANSCODER-262K
    7. 234683
    Prev
    Next
    INDEX
    Explanations

    of

    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_46_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
    igita
    0.41
    pup
    0.41
    education
    0.40
    jeu
    0.38
    ré
    0.38
    賛
    0.38
    Education
    0.37
    绯
    0.37
     生
    0.36
    逸
    0.36
    POSITIVE LOGITS
     Garbage
    0.43
     Gad
    0.42
    ༼
    0.39
     Cair
    0.38
    markdown
    0.37
    ホー
    0.37
     finisher
    0.36
    ாய
    0.35
     kaun
    0.35
     Markdown
    0.35
    Activations Density 0.000%

    No Known Activations