© 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. 56-GEMMASCOPE-2-TRANSCODER-262K
    7. 208316
    Prev
    Next
    INDEX
    Explanations

    m

    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
    revise
    0.40
    oncé
    0.38
    ย
    0.37
     Licensing
    0.37
    Rev
    0.36
    kusen
    0.36
    အရ
    0.36
    ل
    0.36
    found
    0.35
    sup
    0.35
    POSITIVE LOGITS
     d
    0.52
     percents
    0.44
     PERCENT
    0.42
    %\
    0.39
    ścić
    0.38
     "="
    0.38
    ския
    0.38
     (%)
    0.38
    갑습니다
    0.38
    ilarly
    0.38
    Activations Density 0.001%

    No Known Activations