© 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. 22-GEMMASCOPE-2-TRANSCODER-262K
    7. 258269
    Prev
    Next
    INDEX
    Explanations

    sets up questions

    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_22_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
    zentrum
    0.29
    kenalkan
    0.28
    ത്തുന്ന
    0.26
     prest
    0.26
    Duration
    0.25
    testng
    0.25
    Ϯ
    0.24
    KN
    0.24
    Khan
    0.24
     ill
    0.24
    POSITIVE LOGITS
     AR
    0.32
     Fridge
    0.31
     fridge
    0.30
    AR
    0.27
    シー
    0.27
     PCIe
    0.27
     Piping
    0.27
     RTR
    0.27
    ित्व
    0.27
     interstate
    0.27
    Activations Density 0.007%

    No Known Activations