© 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. 40-GEMMASCOPE-2-TRANSCODER-262K
    7. 552
    Prev
    Next
    INDEX
    Explanations

    body energy expenditure

    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_40_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
    formatter
    0.45
    expiration
    0.43
    เอา
    0.41
    㞒
    0.40
     سلم
    0.38
    বদ্ধ
    0.38
    atelier
    0.38
     ದೇವರ
    0.38
    ᓇ
    0.38
    ⸩
    0.37
    POSITIVE LOGITS
     investments
    0.51
     sixth
    0.47
     type
    0.44
     Investments
    0.43
     organ
    0.42
     substrate
    0.39
     produces
    0.39
     desta
    0.39
     organes
    0.39
     clears
    0.39
    Activations Density 0.061%

    No Known Activations