© 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. 168985
    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_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
     hoạch
    0.41
    జు
    0.40
    сибир
    0.39
     insuf
    0.38
     ग़
    0.37
     державного
    0.35
    holt
    0.35
     ғ
    0.35
     Novosibirsk
    0.34
     agon
    0.34
    POSITIVE LOGITS
     단
    1.92
    團
    1.66
    団
    1.64
    团
    1.40
     đoàn
    1.36
     single
    1.35
    단
    1.33
    Single
    1.31
    single
    1.30
     Single
    1.27
    Activations Density 0.000%

    No Known Activations