© 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. 6-GEMMASCOPE-2-TRANSCODER-262K
    7. 232063
    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_6_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
    <0x82>
    1.05
    ０
    1.04
    <0x80>
    1.03
    <0xB5>
    1.00
    ه
    1.00
    их
    0.96
    <0xAC>
    0.94
    <0xAB>
    0.92
     отмети
    0.92
    <0xF3>
    0.92
    POSITIVE LOGITS
    3
    1.32
     that
    1.12
    he
    1.00
    ,
    0.98
    4
    0.95
    TE
    0.95
    ME
    0.94
    PH
    0.90
     וא
    0.90
    5
    0.90
    Activations Density 0.000%

    No Known Activations