© 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. 250667
    Prev
    Next
    INDEX
    Explanations

    say "punctuation marks"

    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
     p
    0.63
    |"
    0.39
    ürzt
    0.38
     פּ
    0.38
     સૌથી
    0.37
    FormBorderStyle
    0.37
     п
    0.37
     вообще
    0.36
     પ
    0.36
     सहा
    0.36
    POSITIVE LOGITS
     －
    0.46
    －
    0.40
     remotely
    0.39
     пресс
    0.38
     ―
    0.37
     please
    0.37
    通過
    0.36
    又は
    0.36
     Heads
    0.36
     hingga
    0.36
    Activations Density 0.000%

    No Known Activations