© 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. 31209
    Prev
    Next
    INDEX
    Explanations

    New York City agencies

    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
     پوائن
    0.41
     Joe
    0.40
    โจ
    0.39
    年至
    0.39
     Cid
    0.38
    綴
    0.38
     paralyzed
    0.37
    𝕞
    0.36
    惭
    0.36
    栦
    0.36
    POSITIVE LOGITS
    hened
    0.41
     hunter
    0.40
    ダン
    0.40
    cas
    0.40
    UIView
    0.40
    Hunter
    0.39
     ダン
    0.38
    ○
    0.37
     ○
    0.36
     ஊற
    0.36
    Activations Density 0.002%

    No Known Activations