© 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. 20-GEMMASCOPE-2-TRANSCODER-262K
    7. 208421
    Prev
    Next
    INDEX
    Explanations

    dates with slashes

    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_20_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
     Clemson
    0.42
     landscaping
    0.40
    ?
    0.38
     B
    0.38
    aksan
    0.37
     Silverado
    0.37
    钀
    0.37
    ando
    0.36
    𝐥
    0.36
     Sinal
    0.36
    POSITIVE LOGITS
    unzione
    0.44
     méthod
    0.43
    agogues
    0.43
     méthodes
    0.42
     whakar
    0.40
    രുന്നത്
    0.40
    渔
    0.39
    doFilter
    0.39
    వులు
    0.39
     dzień
    0.39
    Activations Density 0.001%

    No Known Activations