© 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. 2-GEMMASCOPE-2-TRANSCODER-262K
    7. 162347
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_2_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
    માં
    1.66
     criticize
    1.50
    ות
    1.38
     stabilize
    1.38
    يا
    1.37
    ية
    1.34
    ２
    1.33
     socialize
    1.31
     modernize
    1.29
     mobilize
    1.28
    POSITIVE LOGITS
    ت
    1.08
    ic
    1.07
    us
    1.06
    v
    1.03
    تج
    1.02
    I
    0.94
    be
    0.89
    n
    0.87
    ling
    0.86
    han
    0.85
    Activations Density 0.000%

    No Known Activations