© 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. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 90483
    Prev
    Next
    INDEX
    Explanations

    pure Python

    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_3_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
     دی
    0.62
     części
    0.61
    𝒎
    0.60
     convient
    0.59
    の影響
    0.59
     می‌کند
    0.59
    کز
    0.59
    یر
    0.58
     کر
    0.58
     فی
    0.58
    POSITIVE LOGITS
     is
    0.71
     I
    0.66
    s
    0.64
    kte
    0.61
    on
    0.60
    ký
    0.60
    다면
    0.60
     able
    0.57
    end
    0.57
    ions
    0.57
    Activations Density 0.003%

    No Known Activations