© 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. 31-GEMMASCOPE-2-TRANSCODER-262K
    7. 32343
    Prev
    Next
    INDEX
    Explanations

    north, south, east, west

    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
    ębior
    0.40
     centred
    0.39
    鵜
    0.38
     Fixing
    0.37
     линии
    0.36
     лінії
    0.36
    哌
    0.36
    ashire
    0.36
    bardziej
    0.35
     কেন্দ
    0.35
    POSITIVE LOGITS
     neighboring
    0.58
    隣
    0.48
     প্রতিবেশী
    0.46
    advers
    0.45
     neighbouring
    0.44
     Neighbor
    0.43
     पड़ोसी
    0.42
     neighbors
    0.40
    neighbor
    0.40
     inh
    0.40
    Activations Density 0.007%

    No Known Activations