© 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. 44-GEMMASCOPE-2-TRANSCODER-262K
    7. 5605
    Prev
    Next
    INDEX
    Explanations

    code formatting artifacts

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_44_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
    鏘
    0.35
    㥉
    0.35
    搆
    0.34
    䄪
    0.33
     Bromley
    0.33
    بلی
    0.32
    stellung
    0.32
    馅
    0.32
    遉
    0.32
    ativen
    0.32
    POSITIVE LOGITS
    腺
    0.33
    >>
    0.31
     ...
    0.31
    Ker
    0.30
    green
    0.30
    losses
    0.30
    >(
    0.29
    Green
    0.28
     ex
    0.28
    ...+
    0.28
    Activations Density 0.000%

    No Known Activations