© 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. 40-GEMMASCOPE-2-TRANSCODER-262K
    7. 30842
    Prev
    Next
    INDEX
    Explanations

    quotes around metadata fields

    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_40_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
    डब्ल्यू
    0.44
    ಫ್
    0.41
    Tommy
    0.41
    GTA
    0.41
     Multip
    0.40
     Welding
    0.40
     Wilhelm
    0.40
    紵
    0.39
     Tommy
    0.39
    Audi
    0.39
    POSITIVE LOGITS
    associate
    0.47
    次
    0.44
    instant
    0.39
    ];//
    0.39
    pliance
    0.38
    ode
    0.37
    put
    0.37
    odan
    0.37
    azy
    0.36
    수에
    0.36
    Activations Density 0.000%

    No Known Activations