© 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. 51-GEMMASCOPE-2-TRANSCODER-262K
    7. 67847
    Prev
    Next
    INDEX
    Explanations

    .

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_51_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
    Cord
    0.42
    গেট
    0.40
     ㅎㅎ
    0.39
    阊
    0.38
    벡
    0.38
    ButtonGroup
    0.37
     plazo
    0.37
     ㅎ
    0.36
     клиентов
    0.36
    醝
    0.36
    POSITIVE LOGITS
    n
    0.48
     ray
    0.47
    enges
    0.45
    omial
    0.44
     n
    0.43
     Ge
    0.42
    ｎ
    0.42
    nce
    0.42
    ndes
    0.41
    ן
    0.41
    Activations Density 0.001%

    No Known Activations