© 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. 7-GEMMASCOPE-2-TRANSCODER-262K
    7. 30321
    Prev
    Next
    INDEX
    Explanations

    feed or ticker symbol

    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_7_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
    .
    0.80
    น
    0.64
    ί
    0.61
    ete
    0.61
    uts
    0.56
    yn
    0.55
    í
    0.55
    ai
    0.54
    ati
    0.53
    אים
    0.52
    POSITIVE LOGITS
    К
    0.72
    ბ
    0.63
    B
    0.63
    ে
    0.62
    أ
    0.61
    ي
    0.60
     exercer
    0.58
     držav
    0.57
    ścio
    0.57
     haría
    0.56
    Activations Density 0.022%

    No Known Activations