© 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. 23-GEMMASCOPE-2-TRANSCODER-262K
    7. 153863
    Prev
    Next
    INDEX
    Explanations

    written by

    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_23_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
     alcoved
    0.50
    ColorEffects
    0.48
    ্দি
    0.48
    悴
    0.48
    ђено
    0.47
     combate
    0.46
     плате
    0.46
    љашње
    0.46
    setScale
    0.45
    󠁴
    0.45
    POSITIVE LOGITS
    g
    0.52
     Vatican
    0.49
     Essen
    0.48
    美国
    0.48
     NOAA
    0.47
     यामुळे
    0.46
    oh
    0.45
     Mounting
    0.45
     MD
    0.44
    1
    0.44
    Activations Density 0.000%

    No Known Activations