© 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. 20-GEMMASCOPE-2-TRANSCODER-262K
    7. 174943
    Prev
    Next
    INDEX
    Explanations

    "real" world

    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_20_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
    ngth
    0.34
    ,“
    0.30
     хотелось
    0.30
     जिसको
    0.28
     холоди
    0.27
    ,…
    0.27
     алкого
    0.26
    ˮ
    0.26
    fl
    0.26
    િંગ
    0.26
    POSITIVE LOGITS
     jay
    0.34
     Galaxies
    0.34
     electrop
    0.33
    يم
    0.32
     arrears
    0.32
     AMAZING
    0.31
     FHWA
    0.31
    軺
    0.31
     utterances
    0.30
     incredible
    0.30
    Activations Density 0.002%

    No Known Activations