© 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. 31-GEMMASCOPE-2-TRANSCODER-262K
    7. 166972
    Prev
    Next
    INDEX
    Explanations

    denies

    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_31_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
    嘈
    0.38
     அர
    0.37
    multipart
    0.37
    mock
    0.37
    horm
    0.36
     nor
    0.36
    bp
    0.36
    mM
    0.35
     ザ
    0.35
    icyclo
    0.34
    POSITIVE LOGITS
     intention
    0.39
     Пере
    0.38
    യിൽ
    0.36
     Options
    0.35
     Penet
    0.35
     Everglades
    0.35
     Pray
    0.35
     Verhältnis
    0.34
     бъдат
    0.34
     Tert
    0.34
    Activations Density 0.001%

    No Known Activations