© 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. 59-GEMMASCOPE-2-TRANSCODER-262K
    7. 146286
    Prev
    Next
    INDEX
    Explanations

    programming comments

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_59_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
     His
    0.47
     -----------
    0.46
     a
    0.44
     With
    0.43
     Cod
    0.43
     You
    0.42
    His
    0.42
     None
    0.41
    Cod
    0.41
     They
    0.40
    POSITIVE LOGITS
    funktionen
    0.43
    ‐
    0.41
    
    0.39
     funções
    0.37
    ⁣
    0.37
    🥘
    0.35
    ‚
    0.35
     ‬
    0.34
    дуу
    0.34
    ：「
    0.34
    Activations Density 0.005%

    No Known Activations