© 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. 6-GEMMASCOPE-2-TRANSCODER-262K
    7. 134287
    Prev
    Next
    INDEX
    Explanations

    traditionally followed by a description of the past

    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_6_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
    ید
    1.14
    ン
    0.83
    чение
    0.80
    お手
    0.75
    ographic
    0.73
    凤
    0.72
    取り組み
    0.71
    CCOCC
    0.70
     overfitting
    0.70
     Komponenten
    0.70
    POSITIVE LOGITS
    j
    1.33
    로
    1.33
    ing
    1.15
    k
    1.14
    л
    1.13
    ल
    1.12
    á
    1.08
    b
    1.05
    z
    1.05
    h
    1.04
    Activations Density 0.002%

    No Known Activations