© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 56-GEMMASCOPE-2-TRANSCODER-262K
    7. 253223
    Prev
    Next
    INDEX
    Explanations

    atmosphere or place

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_56_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
     cool
    0.40
    adamu
    0.37
    ሰ
    0.36
    macd
    0.34
    ChangedEventArgs
    0.34
     COMPLEXES
    0.34
     me
    0.34
     চট্ট
    0.34
     o
    0.33
     pelatihan
    0.33
    POSITIVE LOGITS
     lif
    0.42
    िणी
    0.41
    ិន
    0.39
    enco
    0.39
    nearest
    0.38
     majesty
    0.38
     کجا
    0.37
    .\"
    0.37
     safest
    0.37
     finito
    0.37
    Activations Density 0.002%

    No Known Activations