© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 27-GEMMASCOPE-2-TRANSCODER-262K
    7. 115761
    Prev
    Next
    INDEX
    Explanations

    regular exercise, unique recipes, AI

    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_27_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
    врат
    0.45
    meshes
    0.40
     modules
    0.38
     linemen
    0.37
    ubjects
    0.36
     portrays
    0.36
    婴
    0.35
     depicts
    0.35
    ួល
    0.35
     conveys
    0.34
    POSITIVE LOGITS
    ENEMY
    0.36
    缺失
    0.34
    〃
    0.34
    德
    0.33
     delito
    0.33
     அமைந்துள்ள
    0.33
     دقیق
    0.33
     conforman
    0.33
     المه
    0.32
     سپر
    0.32
    Activations Density 0.014%

    No Known Activations