© 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. 6-GEMMASCOPE-2-TRANSCODER-262K
    7. 205363
    Prev
    Next
    INDEX
    Explanations

    Limitations of

    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_6_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
    و
    1.20
    м
    1.04
     as
    1.00
    ла
    1.00
    но
    0.98
    логи
    0.96
    ны
    0.92
    п
    0.90
    ות
    0.89
    ன்
    0.88
    POSITIVE LOGITS
    '
    1.39
    7
    1.18
    5
    1.13
    D
    1.05
    9
    1.01
    2
    0.99
    b
    0.95
    B
    0.94
    \
    0.94
    ine
    0.93
    Activations Density 0.001%

    No Known Activations