© 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. 231781
    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_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
     to
    0.86
    ق
    0.84
    س
    0.82
     sitcom
    0.75
    ّد
    0.74
     गोयल
    0.73
    سل
    0.71
    ج
    0.70
     пон
    0.70
    ្នែក
    0.70
    POSITIVE LOGITS
    the
    1.20
    The
    1.18
    I
    1.08
    >
    1.07
    :
    1.02
    ;
    1.02
     I
    1.00
    ने
    0.98
    can
    0.98
    It
    0.98
    Activations Density 0.000%

    No Known Activations