© 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. 165412
    Prev
    Next
    INDEX
    Explanations

    pier and foundation components

    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
    ilibre
    0.25
    러스
    0.23
    usura
    0.22
    ॉक
    0.21
     Nauchno
    0.21
    藠
    0.21
     乀
    0.21
    TabLayout
    0.21
    eldorf
    0.21
    ūr
    0.21
    POSITIVE LOGITS
     protest
    0.24
     pericol
    0.22
     recounting
    0.22
    ي
    0.22
     treacherous
    0.22
    י
    0.22
     from
    0.21
     rocky
    0.21
     savage
    0.21
     perilous
    0.21
    Activations Density 0.001%

    No Known Activations