© 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. 61930
    Prev
    Next
    INDEX
    Explanations

    thickness and tolerance

    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
    ва
    0.68
    0.66
    into
    0.64
    си
    0.63
    зи
    0.62
    ти
    0.61
    i
    0.60
    using
    0.60
    пол
    0.60
    ки
    0.58
    POSITIVE LOGITS
    婍
    0.55
    LOLLIPOP
    0.55
    _{*
    0.54
    cę
    0.52
     cią
    0.51
    𝐶
    0.51
    市場
    0.51
    ImageQueue
    0.51
     escánd
    0.51
    கிறது
    0.50
    Activations Density 0.002%

    No Known Activations