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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-4B-IT
    5. 5-GEMMASCOPE-2-TRANSCODER-262K
    7. 3510
    Prev
    Next
    INDEX
    Explanations

    up-to-the-minute

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-4b-it/transcoder_all/layer_5_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
    hellip
    0.68
    çok
    0.66
     Lorentzian
    0.61
    uttu
    0.60
    עת
    0.60
    †
    0.60
    atzeko
    0.59
    ćem
    0.59
    ህል
    0.58
     hev
    0.58
    POSITIVE LOGITS
    ли
    0.73
     diante
    0.62
    н
    0.61
    л
    0.60
    جہاں
    0.59
    勿
    0.58
    к
    0.58
    Примеча
    0.58
     roku
    0.57
    т
    0.57
    Activations Density 0.002%

    No Known Activations