© 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. 41-GEMMASCOPE-2-TRANSCODER-262K
    7. 65587
    Prev
    Next
    INDEX
    Explanations

    code structure markers

    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_41_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
    isPreview
    0.37
    辟
    0.36
     био
    0.36
    شف
    0.36
    दीश
    0.36
     PLHIV
    0.36
    ويض
    0.35
     Secretaries
    0.34
     crebre
    0.34
    ISPW
    0.34
    POSITIVE LOGITS
    >>::
    0.46
    意義
    0.39
     some
    0.39
     overw
    0.39
     algunos
    0.39
     exceso
    0.38
     shrink
    0.38
     நடத்த
    0.38
     constructor
    0.37
     hook
    0.37
    Activations Density 0.000%

    No Known Activations