© 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. 56-GEMMASCOPE-2-TRANSCODER-262K
    7. 168723
    Prev
    Next
    INDEX
    Explanations

    say punctuation

    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
     uk
    0.39
     png
    0.39
     ત્યારે
    0.37
    합
    0.36
     লিখ
    0.36
    라는
    0.35
     rods
    0.35
     Instruments
    0.35
     Фурга
    0.34
     라는
    0.34
    POSITIVE LOGITS
     vis
    0.80
     -
    0.74
     Vis
    0.65
    vis
    0.64
     -"
    0.64
    Vis
    0.63
    --"
    0.54
     $-$
    0.53
    VIS
    0.52
     -!
    0.51
    Activations Density 0.008%

    No Known Activations