© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 57-GEMMASCOPE-2-TRANSCODER-262K
    7. 228536
    Prev
    Next
    INDEX
    Explanations

    :

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_57_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
    brick
    0.42
     skirting
    0.39
    :],
    0.38
    :].
    0.37
    amount
    0.36
    artis
    0.35
    etz
    0.35
    obsc
    0.35
    bricks
    0.34
    ranking
    0.33
    POSITIVE LOGITS
    VENTION
    0.40
     đc
    0.38
    ־
    0.38
    គឺជា
    0.37
    Ports
    0.37
     CONSTRUCTION
    0.36
    ್‌
    0.36
     venant
    0.36
     राम
    0.35
     MO
    0.35
    Activations Density 0.003%

    No Known Activations