© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 36239
    Prev
    Next
    INDEX
    Explanations

    user manuals and data behavior

    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
    "
    0.88
    ’
    0.71
     projeto
    0.70
    '
    0.70
    ()
    0.68
    ון
    0.68
     posao
    0.68
     It
    0.67
    לי
    0.67
    ני
    0.66
    POSITIVE LOGITS
    ab
    0.94
    ak
    0.89
    ang
    0.86
    a
    0.85
    un
    0.83
    akap
    0.79
    ung
    0.78
    지
    0.76
    angun
    0.74
    absch
    0.70
    Activations Density 0.007%

    No Known Activations