© 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. 199400
    Prev
    Next
    INDEX
    Explanations

    data values

    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
    लट
    0.40
    ীত
    0.40
    emm
    0.39
    шие
    0.37
    டக
    0.36
    戸
    0.36
    颁
    0.36
    湮
    0.36
    etis
    0.35
     etk
    0.35
    POSITIVE LOGITS
    v
    0.94
    vin
    0.91
    ve
    0.77
    V
    0.77
    vs
    0.74
    ᴠ
    0.72
    𝘃
    0.72
    ving
    0.70
    vy
    0.70
    VIN
    0.69
    Activations Density 0.018%

    No Known Activations