© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 56-GEMMASCOPE-2-TRANSCODER-262K
    7. 250646
    Prev
    Next
    INDEX
    Explanations

    version numbers

    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_56_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
    到達
    0.35
     rock
    0.34
     an
    0.33
    https
    0.33
    వ్వ
    0.33
    先
    0.33
    ROCK
    0.32
    IF
    0.32
    Logic
    0.32
    Nice
    0.32
    POSITIVE LOGITS
     ulc
    0.41
    ሯ
    0.39
    䏼
    0.38
     clarified
    0.37
    masht
    0.37
     omg
    0.37
     getMenuInflater
    0.36
     coeff
    0.36
    
    0.36
     మార
    0.36
    Activations Density 0.000%

    No Known Activations