© 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. 61580
    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
    '
    1.37
    0
    1.20
    på
    1.15
    g
    1.13
    2
    1.13
    ytt
    1.13
    cence
    1.12
    press
    1.11
    u
    1.10
    gene
    1.09
    POSITIVE LOGITS
    لي
    1.30
    го
    1.29
    يل
    1.20
    شي
    1.20
    ди
    1.18
     a
    1.11
    يع
    1.11
     rápido
    1.10
     personalize
    1.10
     compartido
    1.09
    Activations Density 0.000%

    No Known Activations