© 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. 13-GEMMASCOPE-2-TRANSCODER-262K
    7. 9603
    Prev
    Next
    INDEX
    Explanations

    quantization

    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
    の
    0.48
    的
    0.45
    의
    0.44
     Satur
    0.44
     службы
    0.42
    分離
    0.42
    ные
    0.42
    OneDrive
    0.42
    saturated
    0.41
    пя
    0.41
    POSITIVE LOGITS
    ale
    0.46
    ៦
    0.44
    BeforeCall
    0.43
    𒊕
    0.43
    asti
    0.42
     មាន
    0.42
    ena
    0.42
    体验
    0.42
    டாக
    0.42
     présents
    0.42
    Activations Density 0.048%

    No Known Activations