© 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. 40-GEMMASCOPE-2-TRANSCODER-262K
    7. 6997
    Prev
    Next
    INDEX
    Explanations

    controlling space

    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
     attack
    0.31
    Installed
    0.30
     industrial
    0.30
     Industrial
    0.30
    ATTER
    0.30
     dépôt
    0.29
     هام
    0.29
    淬
    0.29
     nutrition
    0.29
     ইঙ্গ
    0.29
    POSITIVE LOGITS
    Administrator
    0.34
     wykorzyst
    0.34
     ვი
    0.32
     корпора
    0.32
    咎
    0.31
     Administrator
    0.30
    emptyDict
    0.30
    acetamol
    0.30
     ACD
    0.30
    agles
    0.29
    Activations Density 0.024%

    No Known Activations