© 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. 125018
    Prev
    Next
    INDEX
    Explanations

    value time, system problems

    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
    <0x0D>
    0.75
    \}=
    0.75
     to
    0.74
    する
    0.74
    р
    0.72
     którzy
    0.71
    ু
    0.69
    ー
    0.67
     are
    0.66
    یت
    0.65
    POSITIVE LOGITS
    ed
    0.78
    d
    0.75
    e
    0.73
    out
    0.71
    don
    0.68
    dV
    0.67
    nog
    0.66
    ogna
    0.66
    es
    0.64
    Were
    0.64
    Activations Density 0.002%

    No Known Activations