© 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. 32983
    Prev
    Next
    INDEX
    Explanations

    Added comments

    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
     تشکیل
    0.33
     retir
    0.33
    ழி
    0.31
     dok
    0.30
    ácil
    0.30
    数为
    0.30
     چاپ
    0.30
    碾
    0.29
    ListOf
    0.29
    手册
    0.29
    POSITIVE LOGITS
     Films
    0.39
    Films
    0.36
     प्लेस
    0.35
     liberties
    0.35
     adorable
    0.34
     drept
    0.34
    oup
    0.33
    OMe
    0.33
    દ્
    0.33
     \\..
    0.33
    Activations Density 0.005%

    No Known Activations