© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 40-GEMMASCOPE-2-TRANSCODER-262K
    7. 8222
    Prev
    Next
    INDEX
    Explanations

    I am, is

    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_40_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
     proceeds
    0.39
     proceeding
    0.36
    NOTICE
    0.36
    泠
    0.36
     recognizes
    0.36
     proceed
    0.35
     zero
    0.35
     proceeded
    0.34
     quantified
    0.34
    ッキング
    0.34
    POSITIVE LOGITS
     Are
    0.44
     Sparta
    0.41
     Spart
    0.40
    QSpacerItem
    0.40
     Sono
    0.40
    Are
    0.39
    sono
    0.38
    </tfoot>
    0.38
     sono
    0.36
    Spart
    0.36
    Activations Density 0.033%

    No Known Activations