© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 33413
    Prev
    Next
    INDEX
    Explanations

    Pacific Rim, Partnership, loss, Rendering, arrays, cellulitis

    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_3_width_262k_l0_small_affine
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
    ý
    0.69
     can
    0.69
     incite
    0.68
    ца
    0.67
     amplification
    0.67
    inį
    0.67
     indignant
    0.66
    бо
    0.66
     circumstantial
    0.66
    𝘁
    0.65
    POSITIVE LOGITS
    ،
    0.84
    IS
    0.77
    );\
    0.73
    ，
    0.72
    PP
    0.69
    }\
    0.69
    }).
    0.68
    وم
    0.67
    Azure
    0.64
    Expires
    0.64
    Activations Density 0.000%

    No Known Activations