© 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. 217289
    Prev
    Next
    INDEX
    Explanations

    James

    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
     Delegation
    0.39
     Plate
    0.38
    arlas
    0.38
    Getter
    0.38
     Vert
    0.37
     Marlon
    0.37
     복
    0.37
    èvre
    0.37
     JAMA
    0.37
    복
    0.37
    POSITIVE LOGITS
    Can
    0.38
    Dumper
    0.38
    ୫
    0.37
    ल्ली
    0.36
    ্বেও
    0.36
    tuple
    0.36
    onClick
    0.36
    Burst
    0.35
    Without
    0.35
    Garden
    0.35
    Activations Density 0.000%

    No Known Activations