© 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. 172029
    Prev
    Next
    INDEX
    Explanations

    improve or revise text

    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
    仅仅
    0.36
    延伸
    0.36
    ઃ
    0.36
    oucault
    0.35
    ecause
    0.35
     तभी
    0.35
     Akademii
    0.35
    Escol
    0.35
    干部
    0.35
    監査
    0.34
    POSITIVE LOGITS
     boilerplate
    0.39
     portrayal
    0.39
     yok
    0.38
    teren
    0.37
     artistic
    0.37
    टन
    0.35
     чита
    0.35
    頓
    0.35
    utes
    0.35
     marsh
    0.35
    Activations Density 0.001%

    No Known Activations