© 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. 5226
    Prev
    Next
    INDEX
    Explanations

    create table, create app

    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
    ｭ
    2.28
     adequada
    2.21
     getroffen
    2.13
    т
    2.11
    ínű
    2.05
    াজী
    2.04
    িশ
    2.04
     Obtained
    2.03
     présentes
    2.02
     médiane
    2.01
    POSITIVE LOGITS
    /^
    2.43
    hip
    2.25
    ⺀
    2.21
    oč
    2.13
     streptomycin
    2.12
    SAND
    2.10
    امہ
    2.07
    cript
    2.06
    S
    2.06
    euler
    2.03
    Activations Density 0.001%

    No Known Activations