© 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. 11-GEMMASCOPE-2-TRANSCODER-262K
    7. 38903
    Prev
    Next
    INDEX
    Explanations

    New Guinea

    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_11_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
    f
    0.04
    یس
    0.04
     디자인
    0.04
    ennials
    0.04
    w
    0.04
    کن
    0.04
    Creating
    0.04
    Integrating
    0.04
    Agg
    0.04
    angg
    0.04
    POSITIVE LOGITS
     suitors
    0.05
     торго
    0.05
     warships
    0.05
    ي
    0.05
     न
    0.05
     valet
    0.05
     цар
    0.05
     ម
    0.05
     Hôtel
    0.05
    са
    0.04
    Activations Density 0.040%

    No Known Activations