© 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. 61875
    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
    s
    1.84
    d
    1.55
     as
    1.53
    ет
    1.19
    dı
    1.15
    ial
    1.10
    dale
    1.10
    ss
    1.09
    dal
    1.09
    ی
    1.09
    POSITIVE LOGITS
    I
    1.46
    (
    1.42
    {
    1.20
    Y
    1.12
    K
    1.08
    ﺭ
    1.02
     ponad
    1.00
    SUN
    0.99
     \
    0.97
    Ŷ
    0.96
    Activations Density 0.000%

    No Known Activations