© 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. 40-GEMMASCOPE-2-TRANSCODER-262K
    7. 29384
    Prev
    Next
    INDEX
    Explanations

    relative skill ratings

    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_40_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
     karat
    0.38
     บ่
    0.38
    パソコン
    0.37
    ahuan
    0.37
    ዀ
    0.37
     பகி
    0.36
    ipment
    0.36
    屶
    0.36
     القسمه
    0.36
     ہوا
    0.35
    POSITIVE LOGITS
     src
    0.45
     roles
    0.40
     tactical
    0.38
     heat
    0.36
     Flatten
    0.36
     purpose
    0.36
     sic
    0.36
     tactics
    0.35
     objectives
    0.35
    脫
    0.35
    Activations Density 0.007%

    No Known Activations