© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 39-GEMMASCOPE-2-TRANSCODER-262K
    7. 4923
    Prev
    Next
    INDEX
    Explanations

    model

    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_39_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
    >(&
    0.40
    via
    0.38
    VELOP
    0.36
    ＼
    0.35
    building
    0.34
    㗊
    0.33
    дис
    0.33
     sorun
    0.33
     birt
    0.33
     stos
    0.32
    POSITIVE LOGITS
    ollen
    0.43
     Serrurier
    0.40
     observado
    0.38
    睬
    0.37
     observations
    0.37
     সমাধানের
    0.36
    稣
    0.36
     Fru
    0.35
     solitaire
    0.35
     observation
    0.35
    Activations Density 0.002%

    No Known Activations