© 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. 3670
    Prev
    Next
    INDEX
    Explanations

    xml starting tags

    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
    চ্ছে
    2.13
    ים
    2.04
     rods
    1.92
     indifferent
    1.89
     junction
    1.85
     feats
    1.82
     undone
    1.72
    膀
    1.66
    ianz
    1.65
     transom
    1.64
    POSITIVE LOGITS
    goers
    2.27
    că
    1.80
    pus
    1.76
    ký
    1.73
    Р
    1.71
    y
    1.70
     relatifs
    1.68
     lieu
    1.65
     Parmi
    1.64
    asjon
    1.64
    Activations Density 0.001%

    No Known Activations