© 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. 27-GEMMASCOPE-2-TRANSCODER-262K
    7. 121220
    Prev
    Next
    INDEX
    Explanations

    brand names

    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_27_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
    ຢູ່ໃນ
    0.34
     किडनी
    0.33
     }}">
    0.31
     चिल्ड्रन
    0.31
     لیکن
    0.31
    했지만
    0.30
    <0x10>
    0.30
     प्रस्तावित
    0.30
     제시
    0.30
     quizá
    0.30
    POSITIVE LOGITS
     fibres
    0.34
    DX
    0.32
     này
    0.32
    差
    0.31
     fibr
    0.30
    gro
    0.30
     loaders
    0.30
     wave
    0.30
     equipments
    0.30
    blos
    0.29
    Activations Density 0.000%

    No Known Activations