© 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. 46-GEMMASCOPE-2-TRANSCODER-262K
    7. 234741
    Prev
    Next
    INDEX
    Explanations

    commit

    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_46_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
    𝗥
    0.41
    擔
    0.40
     Property
    0.39
     assessments
    0.39
    property
    0.38
     refractive
    0.38
     PROPERTY
    0.37
     regrettable
    0.37
     Perform
    0.37
    惆
    0.37
    POSITIVE LOGITS
     energi
    0.40
    תר
    0.39
    rep
    0.38
    ハリ
    0.38
     fuoco
    0.37
    bias
    0.37
    ahili
    0.37
    Bias
    0.37
    ándose
    0.37
     locks
    0.36
    Activations Density 0.002%

    No Known Activations