© 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. 31-GEMMASCOPE-2-TRANSCODER-262K
    7. 220473
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
    റ
    0.40
     preside
    0.39
     verses
    0.39
     milk
    0.38
     dela
    0.38
     getting
    0.38
     surrounded
    0.38
     presided
    0.38
     boss
    0.38
     presiding
    0.38
    POSITIVE LOGITS
     indiquant
    0.43
    💿
    0.42
     deportivos
    0.42
    스포츠
    0.42
    ostics
    0.41
    тики
    0.41
     ड्रॉप
    0.40
    鸴
    0.40
    Codigo
    0.40
    त्री
    0.39
    Activations Density 0.000%

    No Known Activations