© 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. 2-GEMMASCOPE-2-TRANSCODER-262K
    7. 113165
    Prev
    Next
    INDEX
    Explanations

    vad, gedaan, madár

    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_2_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
    وم
    1.33
    ت
    1.29
    ä
    1.18
    og
    1.16
    し
    1.14
    ט
    1.13
    त
    1.10
    া
    1.09
    프
    1.09
    us
    1.08
    POSITIVE LOGITS
    ’
    1.22
    <0xBB>
    1.09
    the
    1.09
    stion
    1.09
    z
    1.01
    kan
    0.98
    <0x99>
    0.95
    gers
    0.92
    tingham
    0.92
    ן
    0.91
    Activations Density 0.000%

    No Known Activations