© 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. 143343
    Prev
    Next
    INDEX
    Explanations

    faces

    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
    -
    1.78
    h
    1.55
    1.53
    om
    1.50
    0
    1.49
    '
    1.46
    um
    1.45
     be
    1.37
    s
    1.37
    ς
    1.37
    POSITIVE LOGITS
     в
    1.91
    在
    1.89
    К
    1.80
     in
    1.63
    И
    1.49
    도
    1.42
    е
    1.38
    S
    1.37
     في
    1.35
    𝚊
    1.34
    Activations Density 0.001%

    No Known Activations