© 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. 59-GEMMASCOPE-2-TRANSCODER-262K
    7. 145768
    Prev
    Next
    INDEX
    Explanations

    Perspectives

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_59_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
    </h1>
    0.53
     For
    0.52
    ↵
    0.47
    </h2>
    0.45
     Areas
    0.45
    </h4>
    0.44
    </h3>
    0.44
    <start_of_image>
    0.43
     :
    0.43
     tienes
    0.42
    POSITIVE LOGITS
    but
    0.47
    which
    0.43
    Sur
    0.42
    after
    0.42
    Which
    0.40
    Open
    0.38
    After
    0.37
     אך
    0.37
    be
    0.36
    ᵃ
    0.36
    Activations Density 0.000%

    No Known Activations