© 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. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 46572
    Prev
    Next
    INDEX
    Explanations

    object key or criteria

    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_3_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
     OBJECT
    0.97
     objectif
    0.89
     objectives
    0.83
     ожида
    0.79
     Objectives
    0.79
    ע
    0.79
     objet
    0.78
     объек
    0.78
     obiettivo
    0.76
     objective
    0.76
    POSITIVE LOGITS
    '
    1.18
    s
    1.03
    ’
    0.86
    ‘
    0.85
    de
    0.84
    t
    0.84
    in
    0.80
    (
    0.79
    는
    0.76
    بل
    0.71
    Activations Density 0.008%

    No Known Activations