© 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. 2-GEMMASCOPE-2-TRANSCODER-262K
    7. 61027
    Prev
    Next
    INDEX
    Explanations

    explaining

    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_2_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
    out
    1.35
    I
    1.05
     Ukraine
    1.05
    </strong>
    1.04
    </em>
    1.02
    ver
    1.01
     that
    0.98
    पणे
    0.97
    ell
    0.97
    5
    0.95
    POSITIVE LOGITS
    '
    1.68
    ু
    1.34
    то
    1.30
    ле
    1.19
    sü
    1.16
    '$\
    1.10
     técnicos
    1.08
    ྛ
    1.04
     prevista
    1.02
    се
    1.02
    Activations Density 0.001%

    No Known Activations