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. 25-GEMMASCOPE-2-TRANSCODER-262K
    4. 8646
    Prev
    Next
    INDEX
    Explanations

    business and technical

    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_25_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
     репре
    0.64
     Eddington
    0.63
     cooperated
    0.63
    𝔦
    0.63
    odings
    0.62
     jinfo
    0.62
    ')['
    0.61
    鍰
    0.61
     பெண்களுக்கு
    0.61
     pushedAt
    0.61
    POSITIVE LOGITS
    TM
    3.25
     TM
    3.00
    tm
    2.98
    ™
    2.82
     ™
    2.61
     tm
    2.54
    ™.
    2.38
    ™,
    2.35
     ®
    2.35
    ®
    2.29
    Activations Density 0.072%

    No Known Activations