© 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. 57-GEMMASCOPE-2-TRANSCODER-262K
    7. 39109
    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_57_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
    ӟ
    0.36
     adjustment
    0.36
     Spotted
    0.36
    ностей
    0.35
     Wink
    0.34
     retrieved
    0.34
     andar
    0.33
     البشر
    0.33
    を持つ
    0.33
     শ্রেষ্ঠ
    0.33
    POSITIVE LOGITS
     Premises
    0.37
     τί
    0.37
     impose
    0.36
     premises
    0.36
     imposing
    0.36
    $-,
    0.35
    aryn
    0.35
    apeutic
    0.35
     повече
    0.35
    तह
    0.35
    Activations Density 0.000%

    No Known Activations