© 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. 1-GEMMASCOPE-2-TRANSCODER-262K
    7. 130638
    Prev
    Next
    INDEX
    Explanations

    Isabel, Isabelle, Moreau, Allende

    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_1_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
    in
    1.98
    a
    1.63
    s
    1.56
    i
    1.52
    ir
    1.48
    o
    1.45
    ни
    1.41
    as
    1.35
    an
    1.28
    er
    1.27
    POSITIVE LOGITS
    ong
    1.13
    )
    1.05
    。
    1.05
    ),
    1.04
    ).
    1.03
    </h4>
    0.99
    </h3>
    0.96
    ৩
    0.96
    ।
    0.94
    ৬
    0.94
    Activations Density 0.002%

    No Known Activations