© 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. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 87375
    Prev
    Next
    INDEX
    Explanations

    smart contract interface DEX

    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_3_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
    に
    0.77
    Α
    0.76
    は
    0.75
     reverb
    0.74
    Соцмережа
    0.73
    
    0.68
    '[
    0.68
    Му
    0.67
     devotee
    0.67
    ИК
    0.67
    POSITIVE LOGITS
    م
    0.93
    tf
    0.88
    et
    0.80
    m
    0.79
    dan
    0.73
    ش
    0.71
    ம்
    0.70
    t
    0.70
    shaped
    0.67
    ం
    0.67
    Activations Density 0.001%

    No Known Activations