© 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. 4854
    Prev
    Next
    INDEX
    Explanations

    seal

    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
    Dado
    2.17
    is
    1.84
    d
    1.76
    述
    1.73
    idée
    1.72
     traff
    1.72
    蔔
    1.67
    енти
    1.63
    ಣ
    1.61
    未经
    1.60
    POSITIVE LOGITS
    ல்
    2.55
     해도
    2.33
    ভাবে
    2.16
     radially
    2.12
     আওতায়
    2.11
     dictated
    2.10
    𝙲
    2.06
     ironically
    2.06
    leq
    2.05
    ました
    2.05
    Activations Density 0.012%

    No Known Activations