© 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-3-27B-IT
    5. 12-GEMMASCOPE-2-TRANSCODER-262K
    7. 201603
    Prev
    Next
    INDEX
    Explanations

    children, expandable, data, model

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_12_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
     {
    0.44
     PRL
    0.43
     мам
    0.42
     поха
    0.42
     பரு
    0.42
     집
    0.41
     parlement
    0.41
     percentile
    0.41
     gonad
    0.41
     ПП
    0.41
    POSITIVE LOGITS
     करिकुलम
    0.50
    illary
    0.45
    你需要
    0.45
    ischer
    0.43
    你
    0.43
    ští
    0.42
    avista
    0.42
     Tes
    0.41
    ico
    0.40
     dimost
    0.40
    Activations Density 0.004%

    No Known Activations