© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 13-GEMMASCOPE-2-TRANSCODER-262K
    7. 10467
    Prev
    Next
    INDEX
    Explanations

    chart patterns, lifecycle costs, industrial symbiosis, strike, contract

    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
    White
    0.12
    AH
    0.12
    Light
    0.11
    AF
    0.11
    Sub
    0.11
    v
    0.11
    V
    0.11
    Board
    0.10
    리
    0.10
    AK
    0.10
    POSITIVE LOGITS
     impeach
    0.10
     ра
    0.10
     compito
    0.10
     detto
    0.09
     motivating
    0.09
     строго
    0.09
     effectuées
    0.09
     conduct
    0.09
     conductas
    0.09
    '
    0.09
    Activations Density 0.054%

    No Known Activations