© 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. 202107
    Prev
    Next
    INDEX
    Explanations

    performance

    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
     Chemists
    0.46
    Nature
    0.43
    Flatten
    0.38
    raving
    0.37
    iencing
    0.36
    illant
    0.35
    atoms
    0.35
    饰
    0.35
    ▔
    0.35
     Nature
    0.34
    POSITIVE LOGITS
    Sexy
    0.38
    呿
    0.38
     drifts
    0.37
     theoretically
    0.37
     practicality
    0.37
     drifted
    0.37
     കൂ
    0.36
    ismarck
    0.36
    給
    0.35
    लय
    0.35
    Activations Density 0.003%

    No Known Activations