© 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. 153639
    Prev
    Next
    INDEX
    Explanations

    abstract concepts nouns

    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
    దు
    0.42
    뭡
    0.38
     inasmuch
    0.38
     रिली
    0.37
     jokingly
    0.37
     mutilated
    0.36
     ಏನು
    0.36
    ంక
    0.36
     broadest
    0.36
    msbuild
    0.35
    POSITIVE LOGITS
    toArray
    0.36
    依然
    0.35
    偷
    0.35
     wykorzyst
    0.35
    続け
    0.35
     inputArray
    0.34
     clinically
    0.34
    gó
    0.34
     forward
    0.34
    ouro
    0.34
    Activations Density 0.000%

    No Known Activations