© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 12-GEMMASCOPE-2-TRANSCODER-262K
    7. 201756
    Prev
    Next
    INDEX
    Explanations

    tissue

    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_12_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
    jakarta
    0.24
    ✿
    0.23
    light
    0.22
    OL
    0.21
    saxophone
    0.21
    Pat
    0.21
    IL
    0.20
    af
    0.20
    Cafe
    0.20
    Ö
    0.20
    POSITIVE LOGITS
     MILLER
    0.28
     Miller
    0.24
    uvieron
    0.22
     allocated
    0.21
    '
    0.21
     “…
    0.21
     RAL
    0.21
     otro
    0.21
    ューズ
    0.21
     RAT
    0.21
    Activations Density 0.000%

    No Known Activations