© 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. 155946
    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_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
     Line
    0.47
     Metropolitan
    0.45
    Line
    0.43
    forRoot
    0.40
     line
    0.39
    OMET
    0.39
    伖
    0.39
     만족
    0.38
     genomen
    0.38
     lineColorSpace
    0.38
    POSITIVE LOGITS
    ベクトル
    0.42
     type
    0.40
    reci
    0.38
    type
    0.37
     youll
    0.37
    +++
    0.37
    दार
    0.37
    idez
    0.36
    accus
    0.36
    VD
    0.35
    Activations Density 0.000%

    No Known Activations