© 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. 231808
    Prev
    Next
    INDEX
    Explanations

    things to keep in mind

    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
    ון
    0.98
    前
    0.98
    Bu
    0.93
    Page
    0.92
    G
    0.91
    Package
    0.89
    N
    0.89
    J
    0.89
    Packages
    0.88
    Debug
    0.88
    POSITIVE LOGITS
    i
    1.05
    ra
    0.98
    ną
    0.98
    ，“
    0.96
    ،
    0.95
    ي
    0.90
    sti
    0.90
    nings
    0.89
    aría
    0.88
    ig
    0.88
    Activations Density 0.003%

    No Known Activations