© 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. 24-GEMMASCOPE-2-TRANSCODER-262K
    7. 180704
    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_24_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
    O
    0.57
    W
    0.52
    İ
    0.52
    C
    0.51
    Goto
    0.50
     up
    0.49
    Comfort
    0.48
    Q
    0.48
    Up
    0.47
    Z
    0.47
    POSITIVE LOGITS
     juggle
    0.47
     शख
    0.46
    сколько
    0.46
     बेस
    0.44
    нца
    0.44
    toList
    0.43
    nos
    0.43
     पर्स
    0.43
    pence
    0.42
    ליו
    0.42
    Activations Density 0.000%

    No Known Activations