© 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. 25-GEMMASCOPE-2-TRANSCODER-262K
    7. 9185
    Prev
    Next
    INDEX
    Explanations

    javascript code

    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
     Four
    0.71
    បញ្
    0.70
     ge
    0.69
    🌑
    0.69
    Ω
    0.68
    Pose
    0.67
     Sing
    0.65
     vignette
    0.65
     Gal
    0.63
     Exo
    0.63
    POSITIVE LOGITS
    ponge
    0.65
     şehir
    0.65
    nam
    0.64
    시면
    0.64
    nets
    0.64
     Shant
    0.62
    ଛ
    0.62
    িত
    0.61
     টিউ
    0.61
     ব্যান
    0.60
    Activations Density 0.000%

    No Known Activations