© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-4B-IT
    5. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 7076
    Prev
    Next
    INDEX
    Explanations

    question words and commands

    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
    S
    2.05
     TÜ
    2.03
     UFC
    1.97
    Rpc
    1.97
     WTO
    1.95
     АК
    1.91
     AEW
    1.90
     CFT
    1.88
     IRC
    1.85
     LEP
    1.83
    POSITIVE LOGITS
    Í
    1.98
    Č
    1.87
    İ
    1.77
    િ
    1.67
    v
    1.66
     abond
    1.66
    Ç
    1.66
    ING
    1.65
    Jenn
    1.64
    Á
    1.63
    Activations Density 0.079%

    No Known Activations