© 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. 40-GEMMASCOPE-2-TRANSCODER-262K
    7. 17717
    Prev
    Next
    INDEX
    Explanations

    female names, titles

    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_40_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
    bsch
    0.37
    oid
    0.37
    𝙞
    0.35
    anha
    0.35
    Variation
    0.35
    Sense
    0.34
    Layer
    0.34
     درجہ
    0.33
     spin
    0.33
    akum
    0.33
    POSITIVE LOGITS
     Strengthening
    0.44
     strengthening
    0.41
     Strengthen
    0.39
    綴
    0.38
     questioning
    0.38
    博物館
    0.37
     জিজ্ঞাসা
    0.37
     mentioning
    0.37
     gambling
    0.36
     handed
    0.35
    Activations Density 0.006%

    No Known Activations