© 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. 10146
    Prev
    Next
    INDEX
    Explanations

    explico cómo presentar

    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
     as
    0.32
    de
    0.31
    -
    0.31
     at
    0.28
     der
    0.26
     snag
    0.26
    前の
    0.26
     accent
    0.25
     medio
    0.25
     divides
    0.25
    POSITIVE LOGITS
     seznam
    0.30
     메시
    0.29
     측정
    0.29
     정보
    0.29
    messageInfo
    0.29
     }$
    0.28
     listItem
    0.28
     ivvu
    0.28
     كيف
    0.28
     gameState
    0.28
    Activations Density 0.235%

    No Known Activations