© 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. 59-GEMMASCOPE-2-TRANSCODER-262K
    7. 146256
    Prev
    Next
    INDEX
    Explanations

    deep learning concepts

    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_59_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
    s
    0.55
    o
    0.52
    oretically
    0.50
    e
    0.46
    ು
    0.46
    koliko
    0.46
    sime
    0.44
    ы
    0.44
    ুদের
    0.41
    ு
    0.41
    POSITIVE LOGITS
    C
    0.69
    S
    0.46
    Ck
    0.45
    Cs
    0.42
    SN
    0.40
    گیر
    0.40
    CAT
    0.39
    CY
    0.39
    SCH
    0.39
     juf
    0.39
    Activations Density 0.000%

    No Known Activations