© 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. 0-GEMMASCOPE-2-TRANSCODER-262K
    7. 143093
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_0_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
    .
    1.54
    :
    1.35
    is
    1.30
    ere
    1.24
    ins
    1.22
    '
    1.21
    ih
    1.19
    ats
    1.16
    ill
    1.14
    ario
    1.13
    POSITIVE LOGITS
    다
    1.56
    ד
    1.51
    ام
    1.48
    া
    1.48
    스
    1.45
     it
    1.44
    ون
    1.39
    د
    1.39
    し
    1.39
    した
    1.38
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.