© 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. 46-GEMMASCOPE-2-TRANSCODER-262K
    7. 63702
    Prev
    Next
    INDEX
    Explanations

    environment

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_46_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
    REAM
    0.40
    aval
    0.38
    cucumber
    0.38
    붉
    0.38
     বেন
    0.37
     Ruins
    0.36
     geomagnetic
    0.36
     താര
    0.36
    벵
    0.36
    olymer
    0.36
    POSITIVE LOGITS
     environnement
    0.55
     environment
    0.54
     genes
    0.53
     Environment
    0.52
    genes
    0.51
     environments
    0.49
     환경
    0.48
     ماحول
    0.48
     Environ
    0.47
    Environ
    0.45
    Activations Density 0.142%

    No Known Activations