© 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. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 122932
    Prev
    Next
    INDEX
    Explanations

    do not

    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
    Not in Any Lists

    No Comments

    Negative Logits
    ة
    0.91
    ing
    0.86
    의
    0.84
    я
    0.84
    ING
    0.82
    д
    0.79
    </td>
    0.78
    ک
    0.78
    𝘢
    0.76
    ın
    0.74
    POSITIVE LOGITS
    for
    0.58
    abble
    0.56
    过来
    0.55
     I
    0.54
    丆
    0.54
    ozyg
    0.54
     braiding
    0.54
    lov
    0.52
    }\
    0.51
    ట్‌
    0.51
    Activations Density 0.000%

    No Known Activations