© 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. 0-GEMMASCOPE-2-TRANSCODER-262K
    7. 79440
    Prev
    Next
    INDEX
    Explanations

    Exception handling keywords

    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_0_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
    ні
    1.67
    kiej
    1.52
    O
    1.52
    ری
    1.48
    ung
    1.30
    ryk
    1.27
    ها
    1.24
    oll
    1.21
    rit
    1.20
    v
    1.19
    POSITIVE LOGITS
    0
    1.66
    3
    1.48
    로
    1.41
    การ
    1.30
     to
    1.28
     uye
    1.24
    ৫
    1.22
    ции
    1.19
    '
    1.18
    1.17
    Activations Density 0.000%

    No Known Activations