© 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. 27-GEMMASCOPE-2-TRANSCODER-262K
    7. 193736
    Prev
    Next
    INDEX
    Explanations

    until next time

    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_27_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
     MCT
    0.38
    奨
    0.37
    Exclude
    0.37
     equi
    0.36
     flavor
    0.36
     tonic
    0.35
     flavors
    0.35
     продав
    0.35
    OUTH
    0.35
    ものです
    0.34
    POSITIVE LOGITS
    hingga
    0.45
     韩
    0.38
    voerd
    0.37
    spirited
    0.37
    ệp
    0.37
     voork
    0.37
    hyd
    0.37
     Supplemental
    0.36
    UpdatedAt
    0.36
     सूर्
    0.35
    Activations Density 0.000%

    No Known Activations