© 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. 3672
    Prev
    Next
    INDEX
    Explanations

    under the

    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
    Ⲉ
    0.84
     discernment
    0.81
    醌
    0.77
    ocentric
    0.77
     despicable
    0.77
     propensity
    0.75
     sideboard
    0.74
    estimating
    0.73
     candies
    0.73
    MENU
    0.73
    POSITIVE LOGITS
    ق
    0.83
    нің
    0.72
    en
    0.68
    ทธิ
    0.68
    llä
    0.67
             
    0.65
    क
    0.65
    skiej
    0.65
            
    0.64
    ██
    0.62
    Activations Density 0.009%

    No Known Activations