© 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. 3640
    Prev
    Next
    INDEX
    Explanations

    cors middleware

    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
    та
    2.05
    ek
    1.85
    тер
    1.67
    ियम
    1.66
     виде
    1.63
     lure
    1.62
     minima
    1.60
    e
    1.60
     baños
    1.59
    on
    1.58
    POSITIVE LOGITS
    𝕒
    2.37
    𝕤
    2.32
    𝕖
    2.23
    𝕕
    2.12
    𝕣
    2.05
    𝕦
    1.95
    𝕞
    1.90
     tomu
    1.81
    𝕠
    1.81
    ्स
    1.80
    Activations Density 0.000%

    No Known Activations