© 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. 25-GEMMASCOPE-2-TRANSCODER-262K
    7. 129930
    Prev
    Next
    INDEX
    Explanations

    helper or util functions

    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_25_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
    読む
    0.31
     Whether
    0.29
     imminent
    0.29
     —
    0.29
     Quiet
    0.29
     Distinct
    0.29
     Specialties
    0.29
    蹴
    0.29
     Water
    0.28
    以外
    0.28
    POSITIVE LOGITS
    ācijas
    0.36
     فره
    0.35
    əsi
    0.34
    sentences
    0.34
    éléments
    0.34
    सिर
    0.33
     éléments
    0.33
    உங்கள்
    0.32
    啊
    0.32
    푅
    0.32
    Activations Density 0.000%

    No Known Activations