© 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. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 5308
    Prev
    Next
    INDEX
    Explanations

    abbreviations and acronyms

    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_3_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
    गल
    1.30
    ****************
    1.07
    й
    1.06
    neath
    1.03
    {{{
    1.03
    жно
    1.00
    te
    1.00
    na
    0.99
    ines
    0.97
    ning
    0.97
    POSITIVE LOGITS
    rope
    1.35
     coaction
    1.25
     моло
    1.20
     дорогие
    1.19
     jsonObj
    1.19
    ewöhn
    1.18
    𝐘
    1.18
     notValid
    1.17
     pidió
    1.16
    𝘋
    1.16
    Activations Density 0.039%

    No Known Activations