© 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. 53147
    Prev
    Next
    INDEX
    Explanations

    `if` or `namespace` followed by code

    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
    起到
    0.40
     باي
    0.39
    দয়
    0.37
    侧
    0.37
     வி
    0.36
    进口
    0.36
     unabhäng
    0.36
     অসুবিধা
    0.36
    乐
    0.35
     стоит
    0.35
    POSITIVE LOGITS
    oses
    0.42
    ostics
    0.40
    bara
    0.38
    assembly
    0.38
     apology
    0.37
    INGS
    0.36
    ോഷ
    0.34
    aira
    0.34
    ulman
    0.34
    oche
    0.34
    Activations Density 0.001%

    No Known Activations