© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 37-GEMMASCOPE-2-TRANSCODER-262K
    7. 135364
    Prev
    Next
    INDEX
    Explanations

    social media platforms

    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_37_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
     fi
    0.41
    Aes
    0.36
    含
    0.35
    いつも
    0.35
     ब्ल
    0.35
     मिश्रण
    0.34
    kernels
    0.34
     BL
    0.34
    gwin
    0.34
    仏
    0.34
    POSITIVE LOGITS
     disposição
    0.42
     bowler
    0.38
    iousness
    0.37
    utivo
    0.36
    ipot
    0.36
    onent
    0.36
     detr
    0.35
    墠
    0.35
    atorics
    0.35
    orters
    0.35
    Activations Density 0.001%

    No Known Activations