© 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. 40-GEMMASCOPE-2-TRANSCODER-262K
    7. 33030
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_40_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
     castom
    0.38
     Courthouse
    0.37
    চাল
    0.36
     वर्ड
    0.36
    烜
    0.36
    −−
    0.35
    nial
    0.35
    <unused82>
    0.35
    RECEIVED
    0.35
    ModelAdmin
    0.35
    POSITIVE LOGITS
     apprentices
    0.34
     class
    0.34
     genus
    0.34
     polio
    0.33
     longevity
    0.33
     workload
    0.33
     ecology
    0.33
     rad
    0.33
     حرف
    0.33
     flaps
    0.33
    Activations Density 0.000%

    No Known Activations