© 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. 20-GEMMASCOPE-2-TRANSCODER-262K
    7. 170833
    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_20_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
    WHEN
    0.49
    DING
    0.49
    🥱
    0.49
    畨
    0.48
     announc
    0.47
    ANCES
    0.46
    ার্থে
    0.46
    ΤΟ
    0.46
     unbear
    0.46
    ≣
    0.46
    POSITIVE LOGITS
     pathway
    0.48
     poate
    0.44
     proto
    0.43
     adicion
    0.43
     bedrij
    0.43
     környez
    0.43
     свобо
    0.42
     ouvert
    0.42
     self
    0.42
     membrane
    0.42
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.