© 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. 2-GEMMASCOPE-2-TRANSCODER-262K
    7. 112423
    Prev
    Next
    INDEX
    Explanations

    about and url contexts

    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_2_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
    ли
    1.68
    ana
    1.52
    ле
    1.49
    er
    1.44
    ви
    1.22
    erate
    1.20
    ీ
    1.17
    erde
    1.14
    erent
    1.14
    eries
    1.13
    POSITIVE LOGITS
    もう
    1.27
    した
    1.23
    お
    1.13
    Y
    1.13
    یت
    1.12
    ELL
    1.11
    ک
    1.07
    ید
    1.05
    し
    1.04
    考え
    1.03
    Activations Density 0.003%

    No Known Activations