© 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. 3714
    Prev
    Next
    INDEX
    Explanations

    unless they

    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
    楖
    2.08
    𝘪
    1.96
    㖮
    1.91
     voir
    1.90
    𝘵
    1.89
     hydroly
    1.89
    𝙣
    1.88
     gameObject
    1.87
     fáciles
    1.86
     lect
    1.84
    POSITIVE LOGITS
    d
    2.67
    t
    1.52
    m
    1.50
    此之外
    1.46
    b
    1.38
    k
    1.34
    s
    1.33
     तहत
    1.29
    dP
    1.29
     الدولية
    1.26
    Activations Density 0.052%

    No Known Activations