© 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. 2-GEMMASCOPE-2-TRANSCODER-262K
    7. 108080
    Prev
    Next
    INDEX
    Explanations

    indistinguishable from

    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_2_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
     to
    1.56
     on
    1.48
     and
    1.34
    AT
    1.17
    IA
    1.13
     is
    1.09
    PS
    1.09
    0
    1.07
    LS
    1.06
    BS
    1.05
    POSITIVE LOGITS
    ن
    1.44
    ى
    1.22
    ۳
    1.13
    но
    1.10
    تی
    1.10
    ３
    1.08
    る
    1.05
    τή
    1.04
    ні
    1.03
    اسی
    1.03
    Activations Density 0.000%

    No Known Activations