Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-3-4B-IT
    3. 33-GEMMASCOPE-2-TRANSCODER-262K
    4. 261384
    Prev
    Next
    INDEX
    Explanations

    fashion and clothing

    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_33_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
     frustrating
    0.76
     Coroner
    0.73
     Congressman
    0.70
     congressman
    0.66
    crossbow
    0.66
     cannabinoids
    0.65
    簸
    0.64
    annter
    0.63
    ieties
    0.62
     низкой
    0.62
    POSITIVE LOGITS
     TJ
    0.75
     zawiera
    0.75
    钳
    0.75
    linalg
    0.72
    Câu
    0.72
    休暇
    0.71
     ಪ
    0.71
     ప
    0.71
     ไข
    0.70
     टि
    0.70
    Activations Density 0.000%

    No Known Activations