© 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. 25-GEMMASCOPE-2-TRANSCODER-262K
    7. 205721
    Prev
    Next
    INDEX
    Explanations

    field names and identifiers

    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
     evenly
    0.34
     ሰ
    0.34
     constitut
    0.33
     counts
    0.33
     exceeded
    0.33
     audacity
    0.33
     exceeds
    0.32
     Forces
    0.32
    specific
    0.32
     ად
    0.32
    POSITIVE LOGITS
     papá
    0.40
     пап
    0.38
    sgál
    0.38
     себе
    0.37
    FG
    0.37
     idha
    0.37
    👅
    0.37
    bean
    0.37
    uml
    0.37
    enfant
    0.35
    Activations Density 0.009%

    No Known Activations