© 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. 30-GEMMASCOPE-2-TRANSCODER-262K
    7. 54056
    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_30_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
    ئے
    0.50
    㓞
    0.45
     il
    0.43
     reeling
    0.43
     cute
    0.43
     orbiting
    0.42
    檴
    0.41
    تر
    0.40
     rend
    0.39
     mediate
    0.39
    POSITIVE LOGITS
    courts
    0.52
    cored
    0.52
    spl
    0.52
    kern
    0.52
    cof
    0.51
    valve
    0.50
    cutting
    0.49
    cars
    0.48
    Francis
    0.48
    kernel
    0.48
    Activations Density 0.000%

    No Known Activations