© 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. 139497
    Prev
    Next
    INDEX
    Explanations

    crabs

    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
     joueurs
    0.62
     joueur
    0.60
     bowed
    0.55
     scrut
    0.54
    问
    0.54
    此
    0.52
     scouts
    0.52
     considéré
    0.51
    到
    0.51
     defendants
    0.50
    POSITIVE LOGITS
    ceram
    0.57
     Tasma
    0.55
    gespr
    0.55
     ओवर
    0.55
     आर
    0.54
    AndroidManifest
    0.54
    And
    0.54
    Furniture
    0.54
    chrift
    0.53
    嚶
    0.53
    Activations Density 0.001%

    No Known Activations