© 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. 12-GEMMASCOPE-2-TRANSCODER-262K
    7. 201833
    Prev
    Next
    INDEX
    Explanations

    salicylate or Hall

    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_12_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
    ່ນ
    0.15
     lungo
    0.14
     years
    0.14
    人を
    0.14
     persever
    0.14
     libro
    0.14
     sarcastic
    0.13
    율
    0.13
    人文
    0.13
    たら
    0.13
    POSITIVE LOGITS
    reib
    0.14
    vá
    0.13
    Wy
    0.13
    igham
    0.13
     Coun
    0.13
    rence
    0.12
     pptn
    0.12
     rendus
    0.12
    োলার
    0.12
    étrique
    0.12
    Activations Density 0.001%

    No Known Activations