© 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-3-27B-IT
    5. 13-GEMMASCOPE-2-TRANSCODER-262K
    7. 13104
    Prev
    Next
    INDEX
    Explanations

    assembly line production or track record

    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_13_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
    ल
    0.45
    л
    0.45
    வ
    0.43
    Bath
    0.41
    ل
    0.41
     Quis
    0.38
    ল
    0.37
    萩
    0.36
    ค
    0.36
    incredible
    0.35
    POSITIVE LOGITS
    ograma
    0.39
     observational
    0.37
    弦
    0.37
    onya
    0.35
     delta
    0.35
     Segundo
    0.35
     Squadron
    0.35
    azes
    0.35
     YY
    0.35
    она
    0.34
    Activations Density 0.042%

    No Known Activations