© 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. 202900
    Prev
    Next
    INDEX
    Explanations

    cause and effect

    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
    脑
    0.42
    佝
    0.42
    大脑
    0.40
     Nantes
    0.39
    ▄
    0.38
     nginx
    0.38
     brain
    0.37
    ToInt
    0.37
     практике
    0.37
     cue
    0.36
    POSITIVE LOGITS
     ಕಾರ
    0.46
     Ray
    0.42
    Ray
    0.40
     V
    0.40
    驷
    0.39
    Carol
    0.39
    ess
    0.38
    HEL
    0.38
     carol
    0.38
    ট্রোল
    0.38
    Activations Density 0.001%

    No Known Activations