© 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. 4-GEMMASCOPE-2-TRANSCODER-262K
    7. 193379
    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_4_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
    p
    0.45
    Variable
    0.44
    UT
    0.43
    IN
    0.42
    t
    0.40
    w
    0.39
    Protein
    0.38
    r
    0.38
    โต
    0.38
     tenido
    0.38
    POSITIVE LOGITS
    ي
    0.60
    amaya
    0.55
     chc
    0.55
     läng
    0.54
    erweise
    0.54
     kie
    0.53
     hendak
    0.52
    י
    0.52
    ophor
    0.51
    utlich
    0.51
    Activations Density 0.000%

    No Known Activations