© 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. 195576
    Prev
    Next
    INDEX
    Explanations

    ChatGLM

    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
     hyst
    0.46
    ..(
    0.39
     سته
    0.39
     Dtsch
    0.38
     કરતાં
    0.37
    ựng
    0.37
    吘
    0.36
    馴
    0.36
     Rie
    0.35
     nồi
    0.35
    POSITIVE LOGITS
    াহীন
    0.46
     TCR
    0.42
    র্ভাব
    0.39
    diamond
    0.39
    tics
    0.39
    ckenridge
    0.38
     gro
    0.38
     Tribut
    0.37
    Kim
    0.37
    Veh
    0.37
    Activations Density 0.000%

    No Known Activations