© 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. 7-GEMMASCOPE-2-TRANSCODER-262K
    7. 31545
    Prev
    Next
    INDEX
    Explanations

    following articles and punctuation

    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_7_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
    Perspective
    0.34
    ᑉ
    0.31
     kinematic
    0.30
     manifolds
    0.29
    Reactor
    0.29
    Metering
    0.29
     follicles
    0.29
    Affine
    0.29
     cathodes
    0.28
     innings
    0.28
    POSITIVE LOGITS
    es
    0.44
    s
    0.38
    et
    0.38
    ك
    0.37
     Puede
    0.34
    ic
    0.31
    aunque
    0.30
    como
    0.29
    os
    0.29
     небольшой
    0.29
    Activations Density 0.091%

    No Known Activations