© 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. 40-GEMMASCOPE-2-TRANSCODER-262K
    7. 11772
    Prev
    Next
    INDEX
    Explanations

    do_sample=true

    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_40_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
    Limit
    0.40
    limit
    0.38
    ConvertTo
    0.37
    }}/
    0.37
    臂
    0.36
    收到
    0.36
     envió
    0.36
    యర్
    0.36
    กระท
    0.35
    FindFileData
    0.35
    POSITIVE LOGITS
     early
    0.66
    early
    0.64
     Early
    0.60
     EARLY
    0.54
     premature
    0.52
    Early
    0.52
    早
    0.51
     sớm
    0.50
    早期
    0.47
     早
    0.47
    Activations Density 0.003%

    No Known Activations