© 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
    3. Gemma-3-4B-IT
    5. 5-GEMMASCOPE-2-TRANSCODER-262K
    7. 3698
    Prev
    Next
    INDEX
    Explanations

    asking for description

    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
     añad
    1.87
    cules
    1.80
     stockings
    1.80
     Är
    1.80
     conséqu
    1.79
    </iframe>
    1.76
     Tü
    1.76
    ഹമ്മ
    1.75
     Informed
    1.73
     complète
    1.69
    POSITIVE LOGITS
    relativistic
    1.70
    الف
    1.67
    자
    1.55
     hostile
    1.53
    filament
    1.48
    зем
    1.44
    లో
    1.41
    xhr
    1.41
    x
    1.40
    氀
    1.37
    Activations Density 0.019%

    No Known Activations