© 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. 56-GEMMASCOPE-2-TRANSCODER-262K
    7. 23774
    Prev
    Next
    INDEX
    Explanations

    Click

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_56_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
     feature
    0.47
     /
    0.44
    :/
    0.42
    Feature
    0.40
     Feature
    0.40
    ,/
    0.39
     /-
    0.39
     ../
    0.38
     FEATURE
    0.38
    (),
    0.38
    POSITIVE LOGITS
    ing
    0.43
     Through
    0.42
    through
    0.42
    ings
    0.41
     Change
    0.41
    Change
    0.41
    Through
    0.41
     through
    0.39
    ingly
    0.39
    pick
    0.38
    Activations Density 0.009%

    No Known Activations