© 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. 205960
    Prev
    Next
    INDEX
    Explanations

    code block endings and errors

    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
     other
    0.49
    aves
    0.47
     daily
    0.45
     always
    0.42
     exquis
    0.42
     +
    0.41
    ’
    0.41
     spoken
    0.41
     autres
    0.40
     zv
    0.39
    POSITIVE LOGITS
     encontró
    0.48
    dört
    0.47
     исход
    0.46
     sugiere
    0.46
    㖷
    0.46
     ಸಾಧ್ಯ
    0.44
     quedó
    0.44
    ípios
    0.44
     derivadas
    0.44
    ປັນ
    0.44
    Activations Density 0.001%

    No Known Activations