© 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. 20-GEMMASCOPE-2-TRANSCODER-262K
    7. 206541
    Prev
    Next
    INDEX
    Explanations

    exclamations of surprise

    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_20_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
    o
    0.44
     daftar
    0.44
    ai
    0.43
    cw
    0.42
     آہستہ
    0.42
     Pec
    0.41
    ari
    0.41
     circost
    0.41
     Please
    0.40
     =>
    0.40
    POSITIVE LOGITS
     destaque
    0.47
     tantôt
    0.46
     గుర్తు
    0.46
     нако
    0.45
     brighter
    0.44
     особы
    0.42
     scorn
    0.42
     sharper
    0.42
    虫
    0.42
     தாக்கு
    0.41
    Activations Density 0.000%

    No Known Activations