© 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. 13-GEMMASCOPE-2-TRANSCODER-262K
    7. 14952
    Prev
    Next
    INDEX
    Explanations

    even followed by list items

    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_13_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
     incid
    0.45
     అది
    0.42
     intellig
    0.41
     vetted
    0.41
     冖
    0.41
     transparen
    0.40
    <unused2119>
    0.40
     intelig
    0.40
    баты
    0.39
     conten
    0.39
    POSITIVE LOGITS
    as
    0.55
    am
    0.43
    et
    0.43
    an
    0.41
    P
    0.38
    av
    0.38
    war
    0.37
    R
    0.37
    over
    0.37
    妇
    0.36
    Activations Density 0.133%

    No Known Activations