© 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. 56-GEMMASCOPE-2-TRANSCODER-262K
    7. 169915
    Prev
    Next
    INDEX
    Explanations

    colon symbol

    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_56_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
    :_
    0.43
     எனவே
    0.43
     stated
    0.41
    :</
    0.39
     úpl
    0.38
    :-
    0.38
     quindi
    0.38
     above
    0.38
     ಆದ್ದರಿಂದ
    0.37
    :“
    0.36
    POSITIVE LOGITS
    .(
    0.40
    .);
    0.40
     [
    0.37
    [
    0.37
    Program
    0.37
    By
    0.37
     ठिका
    0.37
    wik
    0.36
    ങ്ങ്
    0.36
     )(
    0.36
    Activations Density 0.004%

    No Known Activations