© 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. 13-GEMMASCOPE-2-TRANSCODER-262K
    7. 11367
    Prev
    Next
    INDEX
    Explanations

    ancient Sumerian cuneiform

    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
    كية
    0.59
    ակի
    0.54
     EPA
    0.49
    的一
    0.49
     r
    0.49
    сера
    0.49
     C
    0.48
    קים
    0.47
     regionale
    0.47
    gesamt
    0.47
    POSITIVE LOGITS
     दृष्टि
    0.56
     cruciate
    0.56
    𝗛
    0.53
    where
    0.51
    Ш
    0.50
    choose
    0.50
     مُ
    0.49
    this
    0.49
     برج
    0.49
     دنی
    0.49
    Activations Density 0.010%

    No Known Activations