© 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. 10-GEMMASCOPE-2-TRANSCODER-262K
    7. 51488
    Prev
    Next
    INDEX
    Explanations

    little to

    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_10_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
    ä
    0.50
    and
    0.43
     all
    0.43
    t
    0.42
    AP
    0.40
     A
    0.39
    ers
    0.38
    dS
    0.38
    ARA
    0.38
    SEL
    0.37
    POSITIVE LOGITS
    㤓
    0.40
     proporcionan
    0.37
     constitue
    0.37
     permanece
    0.37
     вероятно
    0.36
     quanto
    0.35
     видимо
    0.35
    ني
    0.35
     divulg
    0.34
     позволи
    0.34
    Activations Density 0.004%

    No Known Activations