© 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. 25-GEMMASCOPE-2-TRANSCODER-262K
    7. 9683
    Prev
    Next
    INDEX
    Explanations

    headers

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-4b-it/transcoder_all/layer_25_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
    Ｘ
    0.89
    X
    0.89
     X
    0.79
    Content
    0.72
     اللّه
    0.72
    報酬
    0.72
     XHTML
    0.70
    getX
    0.68
    XH
    0.68
    ｘ
    0.67
    POSITIVE LOGITS
     head
    0.78
     heads
    0.72
     cabeza
    0.71
     header
    0.71
    header
    0.70
     bomb
    0.68
    head
    0.66
     HEAD
    0.66
     headed
    0.65
    urlencoded
    0.65
    Activations Density 0.021%

    No Known Activations