© 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. 25-GEMMASCOPE-2-TRANSCODER-262K
    7. 206714
    Prev
    Next
    INDEX
    Explanations

    dates following names

    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
     gro
    0.16
     bew
    0.16
    ห
    0.16
    би
    0.16
    स्व
    0.16
     lanc
    0.16
     ristor
    0.16
    на
    0.16
     don
    0.16
     മ
    0.16
    POSITIVE LOGITS
     bitOp
    0.19
     CheckException
    0.17
    AddComponent
    0.17
    ບບ
    0.16
    계를
    0.16
     조건을
    0.16
    机的
    0.16
     hypersurface
    0.16
    interacting
    0.15
    ത്തിന്റെയും
    0.15
    Activations Density 0.001%

    No Known Activations