© 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. 40-GEMMASCOPE-2-TRANSCODER-262K
    7. 12876
    Prev
    Next
    INDEX
    Explanations

    reply

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_40_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
    Loss
    0.39
     PICTURE
    0.38
     निर्वा
    0.37
     homoc
    0.37
     gà
    0.37
    沩
    0.36
    Picklist
    0.36
    LOSS
    0.36
    椁
    0.35
     Colorado
    0.35
    POSITIVE LOGITS
     reply
    2.30
     Reply
    2.19
    reply
    2.14
    Reply
    2.08
     replies
    2.08
     replying
    2.05
     replied
    2.00
     REPLY
    2.00
     Replies
    1.70
    回复
    1.70
    Activations Density 0.085%

    No Known Activations