© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 6-GEMMASCOPE-2-TRANSCODER-262K
    7. 229280
    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
     radiate
    1.09
     is
    0.92
     prairie
    0.87
     you
    0.87
     I
    0.86
     inhibit
    0.86
     dijete
    0.84
     OBJECT
    0.84
     uomini
    0.84
     stabilize
    0.83
    POSITIVE LOGITS
    ut
    1.52
    at
    1.30
    та
    1.25
    á
    1.16
    ge
    1.12
    uk
    1.09
    wt
    1.07
    u
    1.07
    ،
    1.03
    이지만
    1.01
    Activations Density 0.000%

    No Known Activations