© 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. 22-GEMMASCOPE-2-TRANSCODER-262K
    7. 261522
    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_22_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
    lığı
    0.54
    衽
    0.52
     проект
    0.51
    ر
    0.51
     Анато
    0.50
    扡
    0.50
    хождения
    0.49
     анато
    0.49
    癃
    0.49
    匍
    0.48
    POSITIVE LOGITS
     n
    0.50
     signaling
    0.49
     Faz
    0.46
     Middle
    0.46
     communications
    0.46
     commemorating
    0.45
     VAR
    0.45
    azio
    0.45
     N
    0.44
    ated
    0.44
    Activations Density 0.000%

    No Known Activations