© 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. 211626
    Prev
    Next
    INDEX
    Explanations

    bridge the gap

    np_acts-logits-general · gemini-2.5-flash-lite
    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
    Town
    0.32
    OfThe
    0.29
    ゞ
    0.28
     Town
    0.27
    Ga
    0.27
    inery
    0.26
    st
    0.26
     সুস্থ
    0.26
     தொற்று
    0.26
    TokenType
    0.26
    POSITIVE LOGITS
     Boardwalk
    0.30
     persuasion
    0.27
    𝐱
    0.27
     árbol
    0.26
     boardwalk
    0.26
     futbol
    0.26
     Cougars
    0.25
     outfielder
    0.25
     atleta
    0.25
     Timberwolves
    0.25
    Activations Density 0.002%

    No Known Activations