© 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. 108551
    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
    ח
    1.50
    い
    1.30
    ری
    1.21
    ロ
    1.19
    ו
    1.16
    ре
    1.14
    に
    1.14
    한
    1.14
    아
    1.12
    에
    1.11
    POSITIVE LOGITS
    s
    1.63
    to
    1.41
    da
    1.32
    with
    1.25
    nn
    1.25
    z
    1.21
    ség
    1.20
    la
    1.16
    na
    1.16
    tl
    1.13
    Activations Density 0.000%

    No Known Activations