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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-4B-IT
    5. 5-GEMMASCOPE-2-TRANSCODER-262K
    7. 3440
    Prev
    Next
    INDEX
    Explanations

    hexadecimal digit sequences

    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
    ou
    0.46
    ak
    0.43
    ů
    0.42
    িতে
    0.41
    astră
    0.41
    ᵐ
    0.41
    aków
    0.40
    ek
    0.40
    álen
    0.39
    yce
    0.39
    POSITIVE LOGITS
    Пред
    0.51
     hazards
    0.43
    Из
    0.42
    Най
    0.42
    이번
    0.41
     цей
    0.40
     Пред
    0.39
     Ү
    0.39
    Điều
    0.38
    То
    0.38
    Activations Density 0.030%

    No Known Activations