© 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. 19-GEMMASCOPE-2-TRANSCODER-262K
    7. 211901
    Prev
    Next
    INDEX
    Explanations

    University and economics institutions

    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_19_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
     contas
    0.52
    ，”
    0.51
     බ
    0.49
    ”-
    0.45
     captivity
    0.45
    ”、
    0.43
     neglect
    0.42
     перегово
    0.42
     ބ
    0.42
     beso
    0.41
    POSITIVE LOGITS
    </sup>
    0.48
     Similar
    0.46
     Teil
    0.45
    Doch
    0.45
    Coconut
    0.43
     Waffen
    0.43
    éis
    0.43
    偶
    0.42
    Does
    0.42
    teil
    0.41
    Activations Density 0.000%

    No Known Activations