© 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. 142289
    Prev
    Next
    INDEX
    Explanations

    Project

    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
    朩
    0.44
     profiling
    0.41
     commons
    0.40
     write
    0.40
     profile
    0.39
     rescaling
    0.39
     Write
    0.38
     punishment
    0.37
     sweat
    0.37
     variance
    0.37
    POSITIVE LOGITS
    itanie
    0.46
    illions
    0.44
     अरब
    0.40
    ccess
    0.40
    [:
    0.39
     riconosc
    0.39
     *:
    0.39
    ilik
    0.39
    libr
    0.39
    Friendly
    0.38
    Activations Density 0.001%

    No Known Activations