© 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. 31-GEMMASCOPE-2-TRANSCODER-262K
    7. 35311
    Prev
    Next
    INDEX
    Explanations

    numbers followed by 'health'

    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_31_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
     facteur
    0.28
     Targeting
    0.27
    ショップ
    0.25
     বেশী
    0.25
     ridicu
    0.25
    isive
    0.24
    ipment
    0.24
    닥
    0.24
     և
    0.24
    總是
    0.23
    POSITIVE LOGITS
     cinqu
    0.27
     seventy
    0.26
     kin
    0.25
     eighteen
    0.25
     seventeen
    0.25
     sixteen
    0.25
     sixty
    0.25
    十五
    0.25
    %%\
    0.25
    getDay
    0.24
    Activations Density 0.007%

    No Known Activations