© 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. 4-GEMMASCOPE-2-TRANSCODER-262K
    7. 197508
    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_4_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
    די
    0.59
    شی
    0.55
    یم
    0.54
    urali
    0.54
    Ah
    0.53
     스트
    0.51
    לי
    0.50
    棻
    0.48
     jednego
    0.47
     앞에
    0.47
    POSITIVE LOGITS
    h
    0.50
    隍
    0.49
     AcOEt
    0.48
     inappropriately
    0.48
     marshes
    0.47
     Políticas
    0.46
    ávají
    0.46
    هما
    0.46
    ချက်
    0.46
    vVertex
    0.46
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.