© 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
    2. Gemma-3-27B-IT
    3. 50-GEMMASCOPE-2-TRANSCODER-262K
    4. 130233
    Prev
    Next
    INDEX
    Explanations

    care

    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
    gebn
    0.42
     יותר
    0.38
    AttributedString
    0.38
     트리플
    0.37
    Insets
    0.36
    蛛
    0.36
    鴻
    0.36
     Gesamt
    0.36
    vey
    0.35
     更
    0.35
    POSITIVE LOGITS
     taking
    1.30
     Taking
    1.21
    taking
    1.20
    Taking
    1.09
     taker
    0.93
     tomando
    0.86
     takers
    0.83
    taker
    0.81
    tak
    0.79
     tak
    0.73
    Activations Density 0.000%

    No Known Activations