© 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. 243272
    Prev
    Next
    INDEX
    Explanations

    alt text; altruism

    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
    Menus
    0.39
     mixes
    0.36
    ليه
    0.35
     transfert
    0.35
    颶
    0.35
    சூ
    0.34
    providers
    0.33
     rãi
    0.33
    TRANSFER
    0.33
    کیل
    0.33
    POSITIVE LOGITS
     Smol
    0.38
    inig
    0.37
    IEEE
    0.37
    alos
    0.37
     ކުރ
    0.37
    omol
    0.35
    olos
    0.35
     waw
    0.34
    ె
    0.34
    inous
    0.33
    Activations Density 0.002%

    No Known Activations