© 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. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 85501
    Prev
    Next
    INDEX
    Explanations

    cos(

    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
    0.81
    🅘
    0.79
    ഌ
    0.78
    用户名
    0.76
    る
    0.76
    Ϥ
    0.76
     fotograf
    0.74
     };
    0.74
     tropas
    0.74
    🅔
    0.73
    POSITIVE LOGITS
    os
    1.49
    is
    1.07
    as
    1.07
    an
    1.00
    1
    0.98
    oft
    0.88
    ات
    0.86
    chter
    0.82
    are
    0.79
    .
    0.79
    Activations Density 0.006%

    No Known Activations