© 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. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 45011
    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_3_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
    r
    0.91
    ر
    0.80
    dni
    0.73
    relation
    0.71
    stion
    0.70
    rst
    0.69
    cL
    0.67
    dN
    0.66
    and
    0.65
    dock
    0.65
    POSITIVE LOGITS
    an
    0.84
     heralded
    0.68
     hydroxide
    0.67
    ش
    0.65
     powied
    0.65
     impeded
    0.64
    inę
    0.63
    ともに
    0.63
     zebrafish
    0.63
     obstructed
    0.62
    Activations Density 0.000%

    No Known Activations