© 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. 40-GEMMASCOPE-2-TRANSCODER-262K
    7. 243487
    Prev
    Next
    INDEX
    Explanations

    history and culture

    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_40_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
     चॉकलेट
    0.41
    Pick
    0.40
    苦
    0.39
    பட்ட
    0.38
     конф
    0.38
     алкого
    0.37
    霖
    0.37
     reconnu
    0.37
     Kamb
    0.37
    ="{
    0.37
    POSITIVE LOGITS
     baked
    0.44
     pillars
    0.42
     trapezium
    0.42
    Baked
    0.41
     pillar
    0.39
     coz
    0.38
    baked
    0.38
     baking
    0.37
     bake
    0.37
     Clayton
    0.37
    Activations Density 0.014%

    No Known Activations