© 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. 120685
    Prev
    Next
    INDEX
    Explanations

    building for ages

    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
    ecas
    0.34
    ล็อก
    0.32
    Datasets
    0.32
    ؍
    0.32
    墳
    0.31
    لمان
    0.31
    databases
    0.31
    ଧ
    0.31
     Pine
    0.31
    лога
    0.31
    POSITIVE LOGITS
    ジュ
    0.34
     phối
    0.34
     Вообще
    0.32
     VPS
    0.30
     minima
    0.29
     coordin
    0.29
     espectadores
    0.29
     coordinates
    0.28
     maxHeight
    0.28
     빠른
    0.28
    Activations Density 0.001%

    No Known Activations