© 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. 34-GEMMASCOPE-2-TRANSCODER-262K
    7. 18497
    Prev
    Next
    INDEX
    Explanations

    define blocks

    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_34_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
     elimin
    0.41
     असल्याची
    0.41
     menghilangkan
    0.39
    Elim
    0.38
     nessun
    0.37
     ликви
    0.36
     消
    0.36
     Elimination
    0.35
    
    0.35
    事情
    0.35
    POSITIVE LOGITS
     boundaries
    0.93
     boundary
    0.86
    boundaries
    0.86
     demarcation
    0.83
     Boundaries
    0.82
     demarc
    0.81
    boundary
    0.79
     delineation
    0.75
     delineate
    0.73
    Boundary
    0.71
    Activations Density 0.035%

    No Known Activations