© 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. 0-GEMMASCOPE-2-TRANSCODER-262K
    7. 82480
    Prev
    Next
    INDEX
    Explanations

    hashlib.sha256 or hashlib.md5

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_0_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
    是
    2.02
    ский
    1.47
    ő
    1.44
    를
    1.33
    就
    1.32
    可以
    1.31
    很
    1.28
    습니다
    1.27
    是为了
    1.25
    할
    1.25
    POSITIVE LOGITS
    r
    1.79
    l
    1.79
    v
    1.70
    il
    1.69
    k
    1.60
    ip
    1.51
    n
    1.49
    ל
    1.45
    w
    1.41
    in
    1.41
    Activations Density 0.000%

    No Known Activations