© 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. 108051
    Prev
    Next
    INDEX
    Explanations

    Balinese cooking and beds

    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
    .
    1.47
    ik
    1.19
    op
    1.18
    ih
    1.18
    ara
    1.02
    ick
    1.02
    age
    0.99
    ow
    0.99
    -
    0.99
    oon
    0.98
    POSITIVE LOGITS
    크
    1.48
    키
    1.26
    드
    1.24
    ש
    1.23
    비
    1.22
    스
    1.20
    트를
    1.19
    티
    1.16
    기
    1.15
    𝓭
    1.12
    Activations Density 0.000%

    No Known Activations