© 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. 107543
    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
    ات
    1.23
    that
    1.20
    ase
    1.17
    人
    1.09
    ne
    1.06
    was
    1.06
    unts
    1.06
    2
    1.06
    ments
    1.02
    ays
    1.01
    POSITIVE LOGITS
     powied
    1.26
     przyję
    1.16
     añad
    1.16
     поги
    1.15
     използва
    1.14
     rozpoczę
    1.12
     przesz
    1.12
     불구하고
    1.12
     aiut
    1.09
     уви
    1.06
    Activations Density 0.000%

    No Known Activations