© 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. 56-GEMMASCOPE-2-TRANSCODER-262K
    7. 250430
    Prev
    Next
    INDEX
    Explanations

    units of measurement

    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
     آ
    0.49
     آپ
    0.47
     directora
    0.43
    ায়
    0.43
     realise
    0.42
    `);
    0.41
     prioritise
    0.41
     `
    0.41
     ,,
    0.41
     centralised
    0.41
    POSITIVE LOGITS
     viele
    0.66
     vielen
    0.65
    many
    0.59
    Durch
    0.56
    geht
    0.54
    Viele
    0.54
     läuft
    0.52
     Hoffnung
    0.52
    nicht
    0.52
     Vielen
    0.52
    Activations Density 0.002%

    No Known Activations