© 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. 22-GEMMASCOPE-2-TRANSCODER-262K
    7. 45926
    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
    仮
    0.37
     I
    0.36
     agreement
    0.36
     SHORT
    0.36
    先端
    0.36
     susceptibility
    0.36
    FOOT
    0.36
     unless
    0.35
    ᕈ
    0.35
    リ
    0.35
    POSITIVE LOGITS
     Tentang
    0.46
     Kullan
    0.46
     този
    0.45
     असलेला
    0.45
    ocatore
    0.44
    owels
    0.42
    ición
    0.41
    itzar
    0.41
     Itu
    0.40
     koris
    0.40
    Activations Density 0.000%

    No Known Activations