© 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. 152801
    Prev
    Next
    INDEX
    Explanations

    ; prediction

    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
    tras
    0.48
    /=
    0.45
     scouting
    0.44
     essentially
    0.42
     scouts
    0.42
    цтва
    0.42
    essentially
    0.41
    ate
    0.40
     görd
    0.40
     readership
    0.40
    POSITIVE LOGITS
     Cette
    0.50
    跑
    0.50
     Depending
    0.47
    According
    0.45
     According
    0.45
    Denne
    0.44
     কালিক
    0.43
     Nếu
    0.42
     ഉപയോഗ
    0.42
     During
    0.42
    Activations Density 0.001%

    No Known Activations