© 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. 23-GEMMASCOPE-2-TRANSCODER-262K
    7. 150739
    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_23_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
    ↵
    0.64
    t
    0.57
    er
    0.55
    h
    0.51
    u
    0.46
    code
    0.46
     ment
    0.45
    letter
    0.44
    ゙
    0.44
    Protocol
    0.44
    POSITIVE LOGITS
     atrap
    0.55
     arriving
    0.54
     amarilla
    0.53
     momentos
    0.51
     chega
    0.50
     pequeno
    0.50
    ேட்
    0.49
     entrando
    0.49
     incluyendo
    0.49
    ából
    0.48
    Activations Density 0.000%

    No Known Activations