© 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. 41-GEMMASCOPE-2-TRANSCODER-262K
    7. 64264
    Prev
    Next
    INDEX
    Explanations

    chess position

    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_41_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
    )=(\
    0.39
    şu
    0.37
     المنا
    0.36
    ané
    0.36
     Ties
    0.36
    আত
    0.35
    不由
    0.35
    雔
    0.35
    slab
    0.35
    scht
    0.34
    POSITIVE LOGITS
     position
    2.64
     Position
    2.33
    Position
    2.25
    position
    2.23
     posición
    2.09
     posição
    2.05
     POSITION
    2.03
     positions
    1.92
     posizione
    1.91
     posisi
    1.87
    Activations Density 0.005%

    No Known Activations