© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 2-GEMMASCOPE-2-TRANSCODER-262K
    7. 159829
    Prev
    Next
    INDEX
    Explanations

    punctuation and non-alphanumeric characters

    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_2_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
    1.76
    to
    1.64
    s
    1.51
    sl
    1.23
    re
    1.22
     for
    1.21
    j
    1.21
     I
    1.20
    sp
    1.19
    na
    1.13
    POSITIVE LOGITS
    :
    1.53
    ми
    1.45
    ление
    1.45
    א
    1.28
    ৯
    1.23
    ৩
    1.21
    ۹
    1.21
    تين
    1.18
    ة
    1.17
    ası
    1.16
    Activations Density 0.000%

    No Known Activations