© 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. 50-GEMMASCOPE-2-TRANSCODER-262K
    7. 31605
    Prev
    Next
    INDEX
    Explanations

    technical terms

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_50_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
     અનુસાર
    0.43
     Juvenile
    0.39
     CIT
    0.38
     CIO
    0.38
     বেলু
    0.38
     চালাতে
    0.38
    ⵚ
    0.35
     pseudonym
    0.34
     Ducks
    0.34
    囃
    0.34
    POSITIVE LOGITS
     DX
    0.43
    Ober
    0.42
    DX
    0.41
    Override
    0.41
     dxf
    0.41
    Estab
    0.40
    Santos
    0.39
    ober
    0.39
    Kur
    0.39
    Min
    0.39
    Activations Density 0.011%

    No Known Activations