© 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. 122474
    Prev
    Next
    INDEX
    Explanations

    pituitary gland

    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
    شی
    0.86
    ट
    0.83
    که
    0.78
    ㎜
    0.76
    ک
    0.70
    ल
    0.68
    ל
    0.68
    یت
    0.67
    seat
    0.67
    प
    0.67
    POSITIVE LOGITS
    est
    0.64
    ed
    0.63
     etwa
    0.63
    綣
    0.60
     verfü
    0.59
    -
    0.59
    em
    0.55
    ia
    0.54
     heraus
    0.54
     exempel
    0.53
    Activations Density 0.000%

    No Known Activations