© 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. 34-GEMMASCOPE-2-TRANSCODER-262K
    7. 167455
    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_34_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
    marginY
    0.48
    amek
    0.40
    퐈
    0.39
     khỏi
    0.38
    aise
    0.38
    שט
    0.37
     απαι
    0.36
    atual
    0.36
     آباد
    0.36
     acus
    0.35
    POSITIVE LOGITS
    ⊃
    0.38
     *
    0.38
    Coefficient
    0.38
     पुष्प
    0.37
     Shea
    0.37
    只限
    0.37
     icons
    0.36
     ders
    0.36
     Factor
    0.36
     Newspapers
    0.36
    Activations Density 0.000%

    No Known Activations