© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-TRANSCODER-262K
    7. 30606
    Prev
    Next
    INDEX
    Explanations

    product descriptions

    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
     방법을
    0.40
    ifah
    0.39
    上来
    0.38
     attendant
    0.35
     text
    0.35
    displayText
    0.35
    Ⲏ
    0.35
     आल्या
    0.33
    文本
    0.32
     testo
    0.32
    POSITIVE LOGITS
     রক্ষণ
    0.43
    鉀
    0.42
    Reuse
    0.41
     কোম
    0.39
     пище
    0.39
    Tanggal
    0.39
     тен
    0.39
     Accum
    0.39
     বেদ
    0.37
     ფ
    0.37
    Activations Density 0.000%

    No Known Activations