© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 34-GEMMASCOPE-2-TRANSCODER-262K
    7. 16611
    Prev
    Next
    INDEX
    Explanations

    cannot, impossible, cannot, cannot

    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
    Zip
    0.37
    QP
    0.36
     unfolds
    0.36
    zees
    0.36
    녓
    0.35
    ủa
    0.34
    Nepal
    0.34
    璧
    0.33
    ValueSet
    0.33
    ȧ
    0.33
    POSITIVE LOGITS
     cannot
    1.14
     Cannot
    1.08
    Cannot
    1.01
    cannot
    1.01
     нельзя
    1.00
    不能
    0.99
     不能
    0.78
    无法
    0.76
    也不能
    0.76
     CANT
    0.74
    Activations Density 0.080%

    No Known Activations