© 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. 9117
    Prev
    Next
    INDEX
    Explanations

    boy and girl

    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
    мови
    0.69
    ofy
    0.65
    ाइन
    0.65
     file
    0.64
    INE
    0.64
    '].
    0.63
     jind
    0.63
    ทธิ
    0.62
    itl
    0.61
    ěz
    0.61
    POSITIVE LOGITS
    जारी
    0.74
    正
    0.73
     prescription
    0.69
    next
    0.67
     scouts
    0.66
    সপ
    0.65
    friends
    0.64
     Notebook
    0.63
     අධ
    0.63
     Comparative
    0.63
    Activations Density 0.013%

    No Known Activations