© 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. 5153
    Prev
    Next
    INDEX
    Explanations

    code decorators and definitions

    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
    ра
    2.10
    ❚
    2.08
    TION
    2.00
    込み
    1.98
    les
    1.94
    ⟶
    1.92
     sz
    1.87
    퓸
    1.87
    கம்
    1.86
    лити
    1.86
    POSITIVE LOGITS
    cstdlib
    2.52
    న
    2.40
     usersRouter
    2.26
     grips
    2.18
     teil
    2.17
     isset
    2.17
     candlest
    2.17
     Compiler
    2.15
    頰
    2.11
    asted
    2.11
    Activations Density 0.013%

    No Known Activations