© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-TRANSCODER-262K
    7. 78226
    Prev
    Next
    INDEX
    Explanations

    dumbbells

    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_31_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
     accepting
    0.41
     hilltop
    0.40
    卆
    0.39
     aufge
    0.37
    olique
    0.37
     Hill
    0.37
     Platt
    0.36
    platte
    0.36
     Hillsborough
    0.36
     플랫폼
    0.34
    POSITIVE LOGITS
    糠
    0.44
    risch
    0.36
    ̴
    0.36
    invisible
    0.36
    Romania
    0.36
    Wrist
    0.36
    circuit
    0.35
    ethash
    0.35
    એસ
    0.35
    ਿਹ
    0.35
    Activations Density 0.055%

    No Known Activations