© 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. 11-GEMMASCOPE-2-TRANSCODER-262K
    7. 245531
    Prev
    Next
    INDEX
    Explanations

    awards

    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_11_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
    腖
    0.71
    utrient
    0.71
    itsky
    0.67
    这个
    0.66
     ทํา
    0.65
    तें
    0.65
    enziale
    0.65
     ಸೂ
    0.65
    hires
    0.64
    ★★★
    0.63
    POSITIVE LOGITS
     courage
    0.55
    von
    0.55
     connected
    0.54
    लम
    0.48
     connectedness
    0.48
     triumph
    0.46
     Catholicism
    0.46
     compensation
    0.46
    vom
    0.46
     Compens
    0.46
    Activations Density 0.000%

    No Known Activations