© 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. 27-GEMMASCOPE-2-TRANSCODER-262K
    7. 117715
    Prev
    Next
    INDEX
    Explanations

    numbers followed by units or quantities

    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_27_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
    wald
    0.41
    ᔕ
    0.38
     estadio
    0.37
     scritta
    0.35
     ступен
    0.35
    ಕ್ಕು
    0.35
     concession
    0.35
     ক্ষেত্র
    0.35
     SCIENCES
    0.34
    ppet
    0.34
    POSITIVE LOGITS
    葢
    0.32
     nesta
    0.31
     పోలీసులు
    0.31
    فاظ
    0.30
    白い
    0.30
    Merhaba
    0.30
    विण्यात
    0.30
    재
    0.30
     tartoz
    0.30
    纹
    0.30
    Activations Density 0.002%

    No Known Activations