© 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. 37-GEMMASCOPE-2-TRANSCODER-262K
    7. 139442
    Prev
    Next
    INDEX
    Explanations

    agreement and comparison

    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_37_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
    ())->
    0.38
     pant
    0.37
    Conn
    0.37
     ju
    0.36
    щини
    0.35
    IVATE
    0.35
    課
    0.35
    réal
    0.35
    ‸
    0.34
    식회사
    0.34
    POSITIVE LOGITS
     agreement
    1.59
     согла
    1.47
    agreement
    1.46
     Agreement
    1.45
     agree
    1.42
     agrees
    1.38
     agreeing
    1.37
     Agree
    1.25
    Agreement
    1.24
     agreements
    1.23
    Activations Density 0.000%

    No Known Activations