© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 25-GEMMASCOPE-2-TRANSCODER-262K
    7. 206110
    Prev
    Next
    INDEX
    Explanations

    technical and non-technical audiences

    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_25_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
    Along
    0.41
    SMITH
    0.41
    Layer
    0.40
    DMSO
    0.40
    ☉
    0.40
     consistente
    0.40
    ροφο
    0.39
     limitada
    0.39
    ыз
    0.39
     wichtiger
    0.39
    POSITIVE LOGITS
    こ
    0.37
     Things
    0.37
     Cz
    0.37
     Ches
    0.37
    Cz
    0.36
     bed
    0.36
    asca
    0.35
     Routine
    0.35
     관리
    0.34
     Mich
    0.34
    Activations Density 0.001%

    No Known Activations