© 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. 20-GEMMASCOPE-2-TRANSCODER-262K
    7. 175101
    Prev
    Next
    INDEX
    Explanations

    .py files

    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_20_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
     overwhelmingly
    0.35
     තම
    0.34
     época
    0.34
    ్యంలో
    0.33
    PathTemplate
    0.32
    뭡
    0.32
    falt
    0.31
    暧
    0.31
     gamblers
    0.30
     exager
    0.30
    POSITIVE LOGITS
     stairway
    0.35
    Content
    0.32
    Muhammad
    0.32
    μου
    0.32
    Interfaces
    0.32
     Mohammad
    0.32
     محمد
    0.31
    杜
    0.30
     Aviation
    0.30
     CCTV
    0.30
    Activations Density 0.001%

    No Known Activations