© 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. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 5624
    Prev
    Next
    INDEX
    Explanations

    manner or degree

    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_3_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
    er
    1.26
    el
    1.12
    tte
    1.03
    lere
    0.98
    aan
    0.97
    ွမ်း
    0.95
    %(
    0.93
    eritud
    0.92
    a
    0.91
    ျေး
    0.90
    POSITIVE LOGITS
     douceur
    0.98
    ের
    0.92
     Durchmesser
    0.91
     हद
    0.91
     ώστε
    0.91
     Abstand
    0.89
    т
    0.89
    સી
    0.87
     Entfer
    0.86
     себя
    0.85
    Activations Density 0.160%

    No Known Activations