© 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. 31-GEMMASCOPE-2-TRANSCODER-262K
    7. 163360
    Prev
    Next
    INDEX
    Explanations

    date of

    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_31_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
    冎
    0.46
     serves
    0.37
     센
    0.36
    詳
    0.36
     grids
    0.36
    掝
    0.36
    椷
    0.35
     dedicating
    0.35
     چکا
    0.35
     serve
    0.35
    POSITIVE LOGITS
    ).(
    0.39
    nyder
    0.38
    父
    0.36
    हाल
    0.36
     Smy
    0.36
    ruga
    0.35
     fashioned
    0.35
    梘
    0.35
     trou
    0.34
    dist
    0.34
    Activations Density 0.002%

    No Known Activations