© 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. 0-GEMMASCOPE-2-TRANSCODER-262K
    7. 142040
    Prev
    Next
    INDEX
    Explanations

    cause / reason

    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_0_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
    edge
    0.56
     micrographs
    0.46
    筤
    0.46
    ﹔
    0.46
     গৃহে
    0.45
    fixed
    0.45
    تا
    0.44
    still
    0.44
    lying
    0.43
    Predicate
    0.43
    POSITIVE LOGITS
     svaki
    0.49
     neće
    0.49
     pogled
    0.46
     बांग्लादेश
    0.46
    애
    0.46
    야
    0.45
     takeover
    0.45
    ający
    0.45
     gug
    0.45
    agoza
    0.43
    Activations Density 0.000%

    No Known Activations