© 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. 46-GEMMASCOPE-2-TRANSCODER-262K
    7. 199221
    Prev
    Next
    INDEX
    Explanations

    be

    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
     gamb
    0.43
     unavailable
    0.42
    Gamb
    0.38
    ที่ไม่
    0.37
     terc
    0.37
     Gamb
    0.36
     घाट
    0.35
    睫
    0.34
    亾
    0.34
     nod
    0.34
    POSITIVE LOGITS
     editar
    0.44
     customised
    0.43
     Customized
    0.40
     mT
    0.39
    âtre
    0.38
     Fixing
    0.38
     cautious
    0.38
     customized
    0.38
    showAlert
    0.37
     funny
    0.37
    Activations Density 0.001%

    No Known Activations