© 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. 24-GEMMASCOPE-2-TRANSCODER-262K
    7. 180601
    Prev
    Next
    INDEX
    Explanations

    temperature degrees Celsius

    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_24_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
    ODO
    0.13
     hypersurfaces
    0.13
    瘢
    0.13
    odyne
    0.13
     psyched
    0.13
    𝑌
    0.13
    नाडा
    0.12
    Teri
    0.12
    स्पून
    0.12
     parete
    0.12
    POSITIVE LOGITS
     fiesta
    0.12
    。
    0.12
     Performance
    0.11
     l
    0.11
    })
    0.11
     Achievements
    0.11
     ed
    0.11
     v
    0.11
     performance
    0.11
    。\
    0.11
    Activations Density 0.000%

    No Known Activations