© 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
    2. Gemma-3-4B-IT
    3. 5-GEMMASCOPE-2-TRANSCODER-262K
    4. 3289
    Prev
    Next
    INDEX
    Explanations

    DNA and RNA bases

    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
    А
    0.79
     Zahl
    0.75
    ली
    0.73
    ти
    0.73
     Объ
    0.73
    pulsewidth
    0.66
    ifornia
    0.64
    ראל
    0.64
    ்ப
    0.63
    osing
    0.63
    POSITIVE LOGITS
    cence
    0.83
    ب
    0.79
    devil
    0.74
    nearest
    0.73
    nath
    0.73
    cutoff
    0.72
    have
    0.71
     retinol
    0.71
     attributable
    0.71
    gathering
    0.69
    Activations Density 0.060%

    No Known Activations