© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-3-27B-IT
    3. 38-GEMMASCOPE-2-TRANSCODER-262K
    4. 2891
    Prev
    Next
    INDEX
    Explanations

    feet, 6, 7

    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_38_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
     wings
    0.48
     wing
    0.42
    bingen
    0.40
    Bren
    0.40
    翼
    0.39
     bree
    0.38
    wicz
    0.38
     Wing
    0.38
    wings
    0.37
    astu
    0.37
    POSITIVE LOGITS
     Lion
    0.49
     accidente
    0.46
    Lion
    0.43
     컨트롤
    0.43
     हाद
    0.42
     Furious
    0.42
     lion
    0.40
    狮
    0.40
     delegations
    0.39
     മെ
    0.39
    Activations Density 0.005%

    No Known Activations