© 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
    3. Gemma-3-27B-IT
    5. 12-GEMMASCOPE-2-TRANSCODER-262K
    7. 139073
    Prev
    Next
    INDEX
    Explanations

    Physically Based Rendering / Roughness

    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
     Notebook
    0.52
    Notebook
    0.51
    ᴿ
    0.50
     సంవత్స
    0.48
    LogIn
    0.45
     oktober
    0.45
    ᔕ
    0.45
    🗸
    0.45
     आक्रमण
    0.45
     Essen
    0.44
    POSITIVE LOGITS
    e
    0.55
     routines
    0.52
    es
    0.50
     reassure
    0.46
    ει
    0.46
     gateways
    0.44
    emde
    0.43
    ת
    0.43
    ید
    0.42
     usefulness
    0.42
    Activations Density 0.002%

    No Known Activations