© 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. 12-GEMMASCOPE-2-TRANSCODER-262K
    7. 198549
    Prev
    Next
    INDEX
    Explanations

    Answer in

    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_12_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
     Tjiwarl
    0.52
    Akt
    0.52
     ativid
    0.50
     tumeur
    0.49
    Codigo
    0.49
    ymbol
    0.48
    ègues
    0.47
     ټ
    0.46
    Chk
    0.46
     tumours
    0.46
    POSITIVE LOGITS
    ered
    0.48
    ịn
    0.47
     cargo
    0.47
    率先
    0.45
    ford
    0.45
    ần
    0.45
    因
    0.44
    玼
    0.44
     F
    0.43
    spiracy
    0.42
    Activations Density 0.000%

    No Known Activations