© 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. 59-GEMMASCOPE-2-TRANSCODER-262K
    7. 63450
    Prev
    Next
    INDEX
    Explanations

    multiple languages

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_59_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
    не
    0.53
     rumor
    0.45
    ning
    0.44
    ner
    0.43
     द
    0.42
     lời
    0.40
    Ner
    0.39
    NER
    0.38
     Ner
    0.38
     rumors
    0.38
    POSITIVE LOGITS
    æ
    0.70
     æ
    0.45
     ver
    0.39
    میٹ
    0.38
    Æ
    0.38
    æl
    0.37
    HEALTH
    0.36
    薇
    0.35
    倒
    0.34
    毒
    0.33
    Activations Density 0.009%

    No Known Activations