© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 27-GEMMASCOPE-2-TRANSCODER-262K
    7. 117281
    Prev
    Next
    INDEX
    Explanations

    COPY command

    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
     report
    0.36
    report
    0.35
    requests
    0.34
     पदार्थ
    0.33
    㕝
    0.33
     específico
    0.33
    璧
    0.33
     competenze
    0.33
    )}}{\
    0.32
    혔
    0.32
    POSITIVE LOGITS
     civilized
    0.35
     Cru
    0.35
    踌
    0.33
    ரிடம்
    0.33
     Baum
    0.32
    我会
    0.32
     McIntosh
    0.32
     porter
    0.32
     Porter
    0.31
     සා
    0.31
    Activations Density 0.001%

    No Known Activations