© 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. 40-GEMMASCOPE-2-TRANSCODER-262K
    7. 5209
    Prev
    Next
    INDEX
    Explanations

    "What" questions or phrases

    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_40_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
     fob
    0.44
     jez
    0.38
     Sita
    0.38
    二
    0.38
     understanding
    0.38
    iatr
    0.37
     lati
    0.36
     diffusione
    0.36
     enough
    0.35
     น
    0.35
    POSITIVE LOGITS
    errick
    0.41
    蟀
    0.41
    Strategies
    0.41
    isAdmin
    0.39
     őket
    0.38
    waitFor
    0.37
    seem
    0.37
    সপ
    0.36
    ແມ່ນ
    0.36
    掉了
    0.36
    Activations Density 0.002%

    No Known Activations