© 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. 2-GEMMASCOPE-2-TRANSCODER-262K
    7. 112880
    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_2_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
    I
    1.61
     is
    1.48
    2
    1.16
    RA
    1.14
    RO
    1.08
    IT
    1.06
    ک
    1.05
     and
    1.02
    ,
    1.02
    PS
    1.00
    POSITIVE LOGITS
    ない
    1.12
    nél
    1.08
    iş
    1.05
    ۰
    1.02
    ların
    1.00
    ação
    0.98
    ת
    0.98
    nine
    0.96
    nimmt
    0.95
    n
    0.95
    Activations Density 0.000%

    No Known Activations