© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 59-GEMMASCOPE-2-TRANSCODER-262K
    7. 60335
    Prev
    Next
    INDEX
    Explanations

    SN

    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
    e
    0.49
    га
    0.40
    ച്ചു
    0.37
    े
    0.37
    致
    0.37
    క
    0.37
    ഷ
    0.37
    sn
    0.37
    sion
    0.37
    ख
    0.36
    POSITIVE LOGITS
    I
    0.84
    IY
    0.54
    TERY
    0.50
    OV
    0.48
    EK
    0.47
    OW
    0.47
    ERO
    0.47
    IFF
    0.46
    IEN
    0.46
    AB
    0.46
    Activations Density 0.000%

    No Known Activations