© 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. 12-GEMMASCOPE-2-TRANSCODER-262K
    7. 138645
    Prev
    Next
    INDEX
    Explanations

    aggregate materials and their processing

    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_12_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
     imaginations
    0.47
    ॉक्स
    0.47
     UD
    0.46
    स्टन
    0.45
     .”
    0.45
    X
    0.44
     पुस्तकें
    0.44
    ASTIC
    0.43
     للد
    0.42
     Tokens
    0.42
    POSITIVE LOGITS
     période
    0.47
     refuse
    0.46
     экономической
    0.46
     characterise
    0.45
    ної
    0.45
     preclude
    0.43
     отказыва
    0.43
     दहेज
    0.43
    ਰ
    0.43
     characterize
    0.43
    Activations Density 0.001%

    No Known Activations