© 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. 13-GEMMASCOPE-2-TRANSCODER-262K
    7. 9181
    Prev
    Next
    INDEX
    Explanations

    left behind

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_13_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
    "
    0.34
    The
    0.31
    Suppose
    0.31
    Right
    0.30
    Like
    0.30
    Play
    0.30
    <b>
    0.29
    We
    0.29
    0
    0.29
    노
    0.29
    POSITIVE LOGITS
     ちゃん
    0.34
    om
    0.33
    ...?
    0.33
    ıç
    0.33
    emu
    0.33
    kyverno
    0.33
    oners
    0.32
    આત
    0.32
    ēs
    0.32
    ího
    0.32
    Activations Density 0.020%

    No Known Activations