© 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. 161644
    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
    т
    1.89
    ти
    1.71
    is
    1.65
    an
    1.55
    et
    1.45
    at
    1.37
    en
    1.31
    ar
    1.27
    ка
    1.21
    as
    1.20
    POSITIVE LOGITS
    1
    1.52
    5
    1.52
    4
    1.47
    K
    1.41
    3
    1.35
    V
    1.30
    H
    1.26
    8
    1.26
    CH
    1.25
    6
    1.23
    Activations Density 0.000%

    No Known Activations