© 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. 56-GEMMASCOPE-2-TRANSCODER-262K
    7. 20403
    Prev
    Next
    INDEX
    Explanations

    Br

    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_56_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
    icious
    0.44
    ice
    0.43
    enco
    0.41
    icularly
    0.36
     botanical
    0.36
    ใช้ง
    0.36
    å
    0.36
    ike
    0.36
    гӀ
    0.36
     bod
    0.35
    POSITIVE LOGITS
    แจ
    0.43
    ۇل
    0.39
    ']),
    0.36
    एंड
    0.34
    ANDE
    0.34
    Unis
    0.33
    ']));
    0.33
    liss
    0.33
     Ubuy
    0.33
    ULU
    0.33
    Activations Density 0.000%

    No Known Activations