Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-3-4B-IT
    3. 33-GEMMASCOPE-2-TRANSCODER-262K
    4. 261959
    Prev
    Next
    INDEX
    Explanations

    .

    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_33_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
    g
    0.88
    kn
    0.85
    k
    0.83
    y
    0.81
    il
    0.80
    ik
    0.77
    ค
    0.76
    n
    0.75
    bk
    0.75
    ко
    0.75
    POSITIVE LOGITS
     NAS
    0.75
    ANDE
    0.74
     perde
    0.73
     Hove
    0.73
     linda
    0.72
    astere
    0.72
     convened
    0.72
    ші
    0.71
     asin
    0.70
     resounding
    0.70
    Activations Density 0.000%

    No Known Activations