© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 13-GEMMASCOPE-2-TRANSCODER-262K
    7. 164746
    Prev
    Next
    INDEX
    Explanations

    strengths and weaknesses

    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
    CHEMICAL
    0.47
    Theoretical
    0.45
    م
    0.42
    м
    0.42
     na
    0.41
    Patients
    0.41
    Premium
    0.41
     chemicals
    0.40
    HEALTH
    0.40
    Chemical
    0.40
    POSITIVE LOGITS
    ută
    0.40
    uffed
    0.39
     {
    0.38
    pros
    0.37
    hato
    0.37
    pard
    0.36
    niej
    0.36
     було
    0.36
    buildCommand
    0.36
    yka
    0.36
    Activations Density 0.019%

    No Known Activations