© 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. 236039
    Prev
    Next
    INDEX
    Explanations

    initial or first

    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
     religiously
    0.33
     analogues
    0.33
    波数
    0.33
     figuratively
    0.33
     discredit
    0.31
    ‍♀
    0.31
     helplessly
    0.31
    _{-
    0.30
     gladly
    0.30
     později
    0.30
    POSITIVE LOGITS
     initial
    0.60
    initial
    0.60
     Initial
    0.57
    Initial
    0.56
     اولیه
    0.50
     inicial
    0.49
    INITIAL
    0.49
     प्रारंभिक
    0.48
     first
    0.48
    нача
    0.47
    Activations Density 0.027%

    No Known Activations