© 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. 3677
    Prev
    Next
    INDEX
    Explanations

    up

    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
    t
    1.78
    cough
    1.63
    र
    1.56
    𝕊
    1.55
     chances
    1.51
    य
    1.51
    <0x89>
    1.45
    場合
    1.40
    ippi
    1.38
    ድረግ
    1.38
    POSITIVE LOGITS
     axioms
    1.68
    健全
    1.67
    Virat
    1.52
    ங்கிணை
    1.51
     nhiễm
    1.50
    槛
    1.50
     stones
    1.46
    elecimento
    1.46
     dinners
    1.42
     proč
    1.40
    Activations Density 0.095%

    No Known Activations