© 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. 88553
    Prev
    Next
    INDEX
    Explanations

    placeholders for team/project names

    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
    s
    0.98
    y
    0.89
    ing
    0.84
    us
    0.82
    ים
    0.80
    اري
    0.79
    αι
    0.78
    n
    0.78
    q
    0.78
    ee
    0.77
    POSITIVE LOGITS
    ،
    0.68
    </h3>
    0.63
    ่
    0.59
     for
    0.58
     sæ
    0.57
    ，”
    0.56
     ป
    0.55
     неё
    0.53
    情节
    0.53
     to
    0.52
    Activations Density 0.001%

    No Known Activations