© 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. 55-GEMMASCOPE-2-TRANSCODER-262K
    7. 49855
    Prev
    Next
    INDEX
    Explanations

    say "C" words

    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_55_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
    meros
    0.43
     dynam
    0.42
    cD
    0.42
    样的
    0.41
    ünft
    0.38
    दुल
    0.38
    cü
    0.38
     D
    0.37
     des
    0.37
     extras
    0.36
    POSITIVE LOGITS
    Kak
    0.43
     Kak
    0.42
    ₁(
    0.41
    Lyric
    0.41
     কল
    0.41
    ᕐ
    0.40
    Toxic
    0.39
    Ax
    0.39
    Python
    0.39
    Lib
    0.38
    Activations Density 0.006%

    No Known Activations