© 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. 56-GEMMASCOPE-2-TRANSCODER-262K
    7. 23045
    Prev
    Next
    INDEX
    Explanations

    popular

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_56_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
     -
    0.48
     Vo
    0.48
     Tran
    0.45
     –
    0.44
     Tru
    0.44
    Tru
    0.44
    Vo
    0.42
     Ngo
    0.42
    Ỷ
    0.42
    Tran
    0.42
    POSITIVE LOGITS
     popular
    0.48
     Popular
    0.47
     zrobić
    0.45
    Popular
    0.44
     populares
    0.39
    ínt
    0.38
    popular
    0.38
    setKeepCallback
    0.37
     beğen
    0.37
     jì
    0.36
    Activations Density 0.006%

    No Known Activations