© 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. 37-GEMMASCOPE-2-TRANSCODER-262K
    7. 135753
    Prev
    Next
    INDEX
    Explanations

    numbers after punctuation marks

    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_37_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
     fif
    0.46
    Obama
    0.45
    ruar
    0.44
     Obama
    0.42
     interfacing
    0.41
     cryptocurrency
    0.39
    ⅞
    0.39
    Examin
    0.39
    തര
    0.39
    olium
    0.38
    POSITIVE LOGITS
     precaution
    0.35
     wish
    0.34
     Прав
    0.33
     슬
    0.33
     reservados
    0.33
     hood
    0.32
    امية
    0.32
     Wish
    0.32
    udem
    0.32
     positional
    0.32
    Activations Density 0.032%

    No Known Activations