© 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. 20999
    Prev
    Next
    INDEX
    Explanations

    b

    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
     lượt
    0.41
    棈
    0.38
    imps
    0.37
    NotExist
    0.37
    itement
    0.37
    linkCell
    0.37
     Visibility
    0.36
    ቶ
    0.36
     ड्रा
    0.36
    గు
    0.35
    POSITIVE LOGITS
     dib
    0.41
     sung
    0.39
    dib
    0.39
     embers
    0.39
     diffuse
    0.38
    Dib
    0.38
    Sandy
    0.37
    álaga
    0.37
    НИЕ
    0.35
    pale
    0.35
    Activations Density 0.009%

    No Known Activations