© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 11-GEMMASCOPE-2-TRANSCODER-262K
    7. 35055
    Prev
    Next
    INDEX
    Explanations

    limited things

    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_11_width_262k_l0_small_affine
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
    ging
    0.59
    ána
    0.59
    Vamos
    0.56
    deh
    0.56
    攽
    0.56
    ire
    0.55
    ála
    0.55
    COMB
    0.55
    abah
    0.54
    𝙈
    0.54
    POSITIVE LOGITS
    т
    0.78
    ר
    0.65
    یک
    0.64
    他の
    0.61
    त
    0.61
    りは
    0.60
    트는
    0.60
    রা
    0.59
    نی
    0.59
     visitor
    0.59
    Activations Density 0.005%

    No Known Activations