© 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. 29-GEMMASCOPE-2-TRANSCODER-262K
    7. 83431
    Prev
    Next
    INDEX
    Explanations

    function evaluation with x

    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_29_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
     cæ
    0.36
     chini
    0.35
    orting
    0.33
    ującego
    0.33
    <unused1>
    0.32
    taste
    0.32
    
    0.32
    cade
    0.32
    iliar
    0.31
    trials
    0.31
    POSITIVE LOGITS
     collection
    0.41
     allowed
    0.38
     permitted
    0.38
     Collection
    0.37
     '
    0.36
    这一点
    0.35
     Ex
    0.34
     avion
    0.34
     ‘
    0.33
     Collections
    0.33
    Activations Density 0.006%

    No Known Activations