© 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. 40-GEMMASCOPE-2-TRANSCODER-262K
    7. 246297
    Prev
    Next
    INDEX
    Explanations

    not to implement

    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
    行う
    0.47
     melakukan
    0.47
    
    0.46
    进行
    0.45
     تحدث
    0.45
     تكلم
    0.44
     partecipare
    0.43
    食べた
    0.43
    开展
    0.42
     participer
    0.42
    POSITIVE LOGITS
     seldom
    0.45
     редко
    0.45
    ibile
    0.44
     refrain
    0.43
     rarely
    0.43
     never
    0.42
    awy
    0.42
     හැකි
    0.40
    嘧
    0.40
     refrained
    0.40
    Activations Density 0.051%

    No Known Activations