© 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. 22-GEMMASCOPE-2-TRANSCODER-262K
    7. 45069
    Prev
    Next
    INDEX
    Explanations

    punctuation marks and code delimiters

    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_22_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
    नान
    0.47
    ✠
    0.43
     retailer
    0.40
    жин
    0.39
    zhong
    0.38
    혐
    0.38
    étrique
    0.38
    லர்
    0.38
     dwie
    0.38
     likely
    0.36
    POSITIVE LOGITS
     منطقة
    0.44
     perfetto
    0.41
     আমাদের
    0.40
    甦
    0.38
     festgelegt
    0.38
     телевиде
    0.38
     Tournament
    0.38
     ہمارے
    0.38
    ujan
    0.38
    ódigo
    0.37
    Activations Density 0.001%

    No Known Activations