© 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. 6-GEMMASCOPE-2-TRANSCODER-262K
    7. 130807
    Prev
    Next
    INDEX
    Explanations

    Kinetic

    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_6_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
     \
    1.02
    '
    0.95
    of
    0.93
    ING
    0.91
    О
    0.89
    S
    0.88
                    
    0.86
     أ
    0.83
    L
    0.82
         
    0.81
    POSITIVE LOGITS
    ва
    0.96
    روس
    0.78
    OL
    0.78
    inė
    0.77
    ان
    0.77
    روں
    0.73
    सँग
    0.73
    ன்
    0.72
     troubleshooting
    0.72
    uoj
    0.71
    Activations Density 0.000%

    No Known Activations