© 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. 29-GEMMASCOPE-2-TRANSCODER-262K
    7. 82612
    Prev
    Next
    INDEX
    Explanations

    understand you're

    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_29_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
     여기까지
    0.42
    Food
    0.41
    ellipsis
    0.41
     साउंड
    0.41
     ?>">
    0.39
    比如
    0.39
     dépasse
    0.38
    귓
    0.38
    bbox
    0.37
    nec
    0.37
    POSITIVE LOGITS
     بعد
    0.41
     ημέ
    0.41
     após
    0.40
     בכל
    0.38
     RNG
    0.38
    靕
    0.37
     hàn
    0.36
     después
    0.36
     ولكن
    0.36
     przyst
    0.35
    Activations Density 0.003%

    No Known Activations