© 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
    2. Gemma-3-27B-IT
    3. 12-GEMMASCOPE-2-TRANSCODER-262K
    4. 139474
    Prev
    Next
    INDEX
    Explanations

    accuracy, distance, last

    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_12_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
    𝚓
    0.46
    dagen
    0.39
    렐
    0.39
    gesteld
    0.38
    tgt
    0.38
     Oiseau
    0.38
    挀
    0.38
    払
    0.38
    𝚗
    0.37
    па
    0.37
    POSITIVE LOGITS
    icion
    0.45
    uz
    0.41
     escucha
    0.40
    istani
    0.38
    anmar
    0.38
    id
    0.37
     मूल्य
    0.36
    weed
    0.36
     необходимые
    0.36
     Су
    0.36
    Activations Density 0.001%

    No Known Activations