© 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. 231590
    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
    j
    1.05
    na
    0.97
    0.97
     A
    0.96
     \
    0.96
     {
    0.93
     C
    0.85
     superar
    0.80
    نا
    0.80
     graceful
    0.79
    POSITIVE LOGITS
    м
    0.96
    TER
    0.90
    多的
    0.90
    Sh
    0.86
    SP
    0.84
    ets
    0.84
    IES
    0.82
    TS
    0.81
    TP
    0.80
    </h3>
    0.79
    Activations Density 0.000%

    No Known Activations