© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 20-GEMMASCOPE-2-TRANSCODER-262K
    7. 172946
    Prev
    Next
    INDEX
    Explanations

    segmented bodies or limbs

    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
    Ⲛ
    0.44
     **)
    0.43
    Isn
    0.42
     Isn
    0.42
    Routes
    0.42
    िग
    0.40
     Operator
    0.40
    Network
    0.40
     <
    0.39
    Adult
    0.39
    POSITIVE LOGITS
     subdiv
    0.45
    nombre
    0.44
    헤
    0.43
     rooft
    0.42
    allist
    0.42
    util
    0.42
     planted
    0.42
    花园
    0.42
     verteilt
    0.42
    evo
    0.42
    Activations Density 0.000%

    No Known Activations