© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-TRANSCODER-262K
    7. 52647
    Prev
    Next
    INDEX
    Explanations

    qualitative analysis acid testing

    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_31_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
    release
    0.40
    Release
    0.37
    Republican
    0.37
     Республи
    0.36
     Release
    0.36
     release
    0.35
     reproducción
    0.35
    强
    0.35
    釋
    0.35
    中最
    0.34
    POSITIVE LOGITS
     Feu
    0.45
    )](
    0.39
    Firestore
    0.39
     feuille
    0.38
     Archer
    0.38
     feather
    0.37
     skater
    0.37
     Fiction
    0.36
     Sink
    0.36
    Workbench
    0.36
    Activations Density 0.011%

    No Known Activations