© 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. 31182
    Prev
    Next
    INDEX
    Explanations

    ellipsis

    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
    MiddleCenter
    0.44
    Stderr
    0.39
    雵
    0.38
    स्ताना
    0.37
    сць
    0.37
    щё
    0.37
     GARC
    0.36
    CIÓN
    0.36
     odit
    0.36
    <\
    0.36
    POSITIVE LOGITS
    gener
    0.41
    ingredients
    0.39
    sequ
    0.39
    evidence
    0.39
    well
    0.38
     yaptığı
    0.37
     எனது
    0.37
    ind
    0.36
    proof
    0.36
    remark
    0.36
    Activations Density 0.031%

    No Known Activations