© 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. 25-GEMMASCOPE-2-TRANSCODER-262K
    4. 9213
    Prev
    Next
    INDEX
    Explanations

    gradio code

    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_25_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
     जाने
    0.63
    foration
    0.59
    옐
    0.58
     penc
    0.58
    萻
    0.58
    documentclass
    0.58
    reon
    0.56
     தீர்
    0.56
    UIManager
    0.56
    ?」
    0.56
    POSITIVE LOGITS
     Spelling
    0.56
    骅
    0.54
     почина
    0.51
    enson
    0.51
     playable
    0.50
     মহল
    0.49
     উত্ত
    0.49
    ագր
    0.49
     invalid
    0.49
     floating
    0.48
    Activations Density 0.001%

    No Known Activations