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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-4B-IT
    5. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 5080
    Prev
    Next
    INDEX
    Explanations

    latex document structure

    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
    mutable
    2.56
    ⚙
    2.42
    ‼️
    2.33
    𝘆
    2.32
    ◽
    2.29
    ☰
    2.20
    न्यू
    2.17
    ◾
    2.16
    as
    2.15
    en
    2.14
    POSITIVE LOGITS
    هم
    2.67
    му
    2.43
    dozen
    2.39
    é
    2.21
    ATORS
    2.14
     dàng
    2.11
     pró
    2.11
    𝘦
    2.11
    stalk
    2.10
    PEND
    2.09
    Activations Density 0.000%

    No Known Activations