© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 22-GEMMASCOPE-2-TRANSCODER-262K
    7. 44587
    Prev
    Next
    INDEX
    Explanations

    code comments and structure

    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_22_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
    Applicant
    0.31
    Exchange
    0.31
    applicant
    0.30
     Missile
    0.30
    Bullet
    0.30
    ଐ
    0.30
     arid
    0.30
     يمكن
    0.30
    rophenyl
    0.30
    Main
    0.30
    POSITIVE LOGITS
     destacó
    0.38
     филь
    0.35
     familias
    0.35
    𝘵
    0.34
     famílias
    0.34
     них
    0.34
     hoera
    0.34
    смотря
    0.33
     طلع
    0.33
     जनक
    0.32
    Activations Density 0.062%

    No Known Activations