© 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. 23-GEMMASCOPE-2-TRANSCODER-262K
    7. 153606
    Prev
    Next
    INDEX
    Explanations

    c++ include headers

    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_23_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
     எண்ணிக்கை
    0.45
     pronouncing
    0.42
     திறன்
    0.41
     新款
    0.40
    ឈ្ម
    0.40
     υπάρχει
    0.39
    跑步
    0.38
    <0xD4>
    0.38
    )_{
    0.38
     चिकित्सा
    0.38
    POSITIVE LOGITS
     varying
    0.41
     LT
    0.38
     couch
    0.35
     sofa
    0.35
    ims
    0.34
     kue
    0.34
     lieutenant
    0.33
     bland
    0.33
     intervene
    0.33
    </div>
    0.33
    Activations Density 0.002%

    No Known Activations