© 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. 3625
    Prev
    Next
    INDEX
    Explanations

    event.current.type

    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
    یتی
    1.38
    it
    1.32
    𝑒
    1.29
    ia
    1.21
    ul
    1.18
    ка
    1.13
    дам
    1.10
    ড়
    1.08
    да
    1.08
    یه
    1.08
    POSITIVE LOGITS
    Sprintf
    1.47
    futbol
    1.39
    kert
    1.39
     navbar
    1.39
    ffect
    1.38
     બ
    1.38
    १
    1.38
     expend
    1.37
    均
    1.36
    CameraOpened
    1.36
    Activations Density 0.001%

    No Known Activations