© 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. 0-GEMMASCOPE-2-TRANSCODER-262K
    7. 78305
    Prev
    Next
    INDEX
    Explanations

    defenseless

    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_0_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
    0
    1.76
    ０
    1.64
    s
    1.46
    siniz
    1.44
    <0x0D>
    1.40
    ০
    1.39
     was
    1.38
    to
    1.38
    lara
    1.37
    ERE
    1.35
    POSITIVE LOGITS
    ل
    1.45
     incendi
    1.34
     artific
    1.30
     autocl
    1.30
     ampli
    1.29
     comprob
    1.27
     divulg
    1.26
     coorden
    1.25
     hiv
    1.24
    ia
    1.23
    Activations Density 0.001%

    No Known Activations