© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-3-4B-IT
    3. 5-GEMMASCOPE-2-TRANSCODER-262K
    4. 3169
    Prev
    Next
    INDEX
    Explanations

    bid, quotation, estimate, lead, offer

    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
     immense
    0.79
    अन्य
    0.71
    énération
    0.70
    lijke
    0.68
    lük
    0.67
    nosť
    0.66
    к
    0.66
    رى
    0.63
    lés
    0.61
    nten
    0.61
    POSITIVE LOGITS
     встречи
    0.63
    }">
    0.59
     iya
    0.58
     кстати
    0.58
    Sodium
    0.57
     Tact
    0.57
    }"),
    0.56
     ветра
    0.55
    eer
    0.55
    =\""
    0.55
    Activations Density 0.124%

    No Known Activations