© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-3-27B-IT
    3. 12-GEMMASCOPE-2-TRANSCODER-262K
    4. 139499
    Prev
    Next
    INDEX
    Explanations

    filesystem **Disk**

    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
    It
    0.17
    Priority
    0.16
    I
    0.16
    Succ
    0.16
    OL
    0.15
    t
    0.15
    Color
    0.15
    Flam
    0.15
    Th
    0.15
    P
    0.15
    POSITIVE LOGITS
     MILLER
    0.15
     kidnapping
    0.14
     quantitative
    0.13
     Reynolds
    0.13
     harassing
    0.13
     RESULTS
    0.13
     hapless
    0.12
     ле
    0.12
     subspaces
    0.12
     “[
    0.12
    Activations Density 0.002%

    No Known Activations