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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 13-GEMMASCOPE-2-TRANSCODER-262K
    7. 165214
    Prev
    Next
    INDEX
    Explanations

    jungle monsters

    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_13_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
     ARP
    0.59
    खड़
    0.57
     +(
    0.56
     drooping
    0.53
     agon
    0.52
     {(
    0.51
    䚯
    0.51
    〠
    0.50
     テーブル
    0.50
    쏴
    0.50
    POSITIVE LOGITS
    yan
    0.59
    y
    0.54
    \_
    0.54
     پہا
    0.53
    RealPath
    0.52
     Hill
    0.48
     mountain
    0.48
     Caves
    0.48
    וריה
    0.48
    igts
    0.47
    Activations Density 0.000%

    No Known Activations