© 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. 37-GEMMASCOPE-2-TRANSCODER-262K
    7. 126909
    Prev
    Next
    INDEX
    Explanations

    SQL id, _ consumption

    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_37_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
    iento
    0.38
     mentors
    0.38
     Duffy
    0.37
     Joshi
    0.37
    からない
    0.37
     gereken
    0.36
    +"/"+
    0.36
     Jos
    0.36
     Sharon
    0.36
     sects
    0.36
    POSITIVE LOGITS
    VL
    0.40
    蔼
    0.39
    抗
    0.36
     Vibration
    0.36
     прошли
    0.35
    摜
    0.35
    globe
    0.35
     द्रव
    0.35
    ಡುವುದ
    0.35
    ப்போ
    0.34
    Activations Density 0.008%

    No Known Activations