© 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. 18583
    Prev
    Next
    INDEX
    Explanations

    is true / is not true

    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_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
    ertid
    0.38
    TAK
    0.38
    chn
    0.36
     downtime
    0.36
    lan
    0.35
     Blackberry
    0.35
    껄
    0.35
     במה
    0.35
     conventional
    0.34
     뜨
    0.34
    POSITIVE LOGITS
     qualify
    0.64
     réuss
    0.57
     sucesso
    0.56
     qualifies
    0.56
     éxito
    0.55
    成功
    0.54
    成功的
    0.52
     موفق
    0.52
     успі
    0.52
    successful
    0.52
    Activations Density 0.105%

    No Known Activations