© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 40-GEMMASCOPE-2-TRANSCODER-262K
    7. 15453
    Prev
    Next
    INDEX
    Explanations

    html code blocks

    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
     grant
    0.42
     বহ
    0.40
     Castle
    0.38
     ша
    0.37
     Tomas
    0.37
     हड़
    0.36
     Foy
    0.36
    >(_
    0.36
     lysosomes
    0.36
    <0xB3>
    0.36
    POSITIVE LOGITS
    xsl
    0.43
     ttl
    0.38
     APP
    0.38
    といった
    0.38
     HelloWorld
    0.37
    ència
    0.36
    ibm
    0.36
    hbs
    0.36
    exports
    0.35
     localizada
    0.35
    Activations Density 0.221%

    No Known Activations