© 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. 29-GEMMASCOPE-2-TRANSCODER-262K
    7. 78805
    Prev
    Next
    INDEX
    Explanations

    those/that followed by motivations, object, emotions, self, choices, decisions, requests, narrative, beliefs

    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_29_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
     displeasure
    0.47
     misdemean
    0.41
     powerless
    0.41
     team
    0.37
    われた
    0.36
    तृ
    0.36
    튿
    0.36
     Smy
    0.36
    ಿಸಬಹುದು
    0.36
     pun
    0.36
    POSITIVE LOGITS
     상
    0.45
    并且
    0.42
    並且
    0.40
     હ
    0.40
              
    0.39
     αξ
    0.39
     ы
    0.38
     जगह
    0.38
     通过
    0.37
     利用
    0.37
    Activations Density 0.003%

    No Known Activations