© 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
    2. Gemma-3-4B-IT
    3. 3-GEMMASCOPE-2-TRANSCODER-262K
    4. 5544
    Prev
    Next
    INDEX
    Explanations

    withered, withering, withers

    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
    ׁ
    3.15
    𝓙
    2.83
    zelfde
    2.69
    它是
    2.66
    ل
    2.65
     Stewardship
    2.61
    he
    2.55
    
    2.53
    وهات
    2.49
    न
    2.48
    POSITIVE LOGITS
     atual
    3.15
     journée
    2.78
     tempos
    2.70
    у
    2.56
    п
    2.56
     Atual
    2.54
    دد
    2.52
     conjunta
    2.49
     verwend
    2.47
     inscre
    2.46
    Activations Density 0.008%

    No Known Activations