© 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. 20-GEMMASCOPE-2-TRANSCODER-262K
    7. 171031
    Prev
    Next
    INDEX
    Explanations

    emphasis for instructions

    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_20_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
    `}
    0.25
    くちゃ
    0.25
    ther
    0.25
    制品
    0.25
    jela
    0.25
    iya
    0.25
    legs
    0.24
     สู
    0.24
    ຸກ
    0.24
     ग
    0.24
    POSITIVE LOGITS
     assurance
    0.26
     assure
    0.25
     CORRECT
    0.25
     Promised
    0.25
     Assurance
    0.25
     NET
    0.25
    اول
    0.25
     corretamente
    0.24
     assur
    0.24
    মনে
    0.24
    Activations Density 0.029%

    No Known Activations