© 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. 25-GEMMASCOPE-2-TRANSCODER-262K
    7. 236517
    Prev
    Next
    INDEX
    Explanations

    standard output/input/error

    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_25_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
     नोटबुक
    0.39
    ophys
    0.39
    %!
    0.39
    )*
    0.38
     certify
    0.37
    cert
    0.36
    acycline
    0.36
    】【
    0.35
    caster
    0.35
    龕
    0.35
    POSITIVE LOGITS
    inplace
    0.40
     braced
    0.39
    挼
    0.39
    Culture
    0.39
     signaled
    0.38
     here
    0.37
     Culture
    0.37
     PPS
    0.37
    orice
    0.37
    SAS
    0.36
    Activations Density 0.002%

    No Known Activations