© 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. 56-GEMMASCOPE-2-TRANSCODER-262K
    7. 22527
    Prev
    Next
    INDEX
    Explanations

    helpful AI assistant

    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_56_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
    generally
    0.55
     generally
    0.50
    Generally
    0.47
     Generally
    0.45
     وړاند
    0.42
     گذشته
    0.41
    戞
    0.38
     Clint
    0.38
    ágenes
    0.37
    غل
    0.36
    POSITIVE LOGITS
     cater
    0.38
     hay
    0.38
     siguiente
    0.38
     Pri
    0.37
     Ender
    0.37
    滇
    0.37
    APH
    0.36
     nivel
    0.36
     whereby
    0.36
     pri
    0.36
    Activations Density 0.003%

    No Known Activations