© 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. 11-GEMMASCOPE-2-TRANSCODER-262K
    7. 39714
    Prev
    Next
    INDEX
    Explanations

    silicon lottery

    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_11_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
    Z
    0.47
    та
    0.47
    тое
    0.46
    Sodium
    0.45
    Spain
    0.44
    зме
    0.44
     debounce
    0.43
    Used
    0.43
    на
    0.43
     :
    0.42
    POSITIVE LOGITS
    lu
    0.50
    lä
    0.44
    corsi
    0.43
    luft
    0.39
    lagen
    0.39
    larını
    0.39
     дня
    0.39
     خط
    0.39
    ritas
    0.39
    llll
    0.38
    Activations Density 0.005%

    No Known Activations