© 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. 24-GEMMASCOPE-2-TRANSCODER-262K
    7. 179756
    Prev
    Next
    INDEX
    Explanations

    bird questions

    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_24_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
    สมัย
    0.42
     readme
    0.41
     В
    0.38
     ovip
    0.38
     topographic
    0.38
     subdomain
    0.38
     github
    0.38
     rivet
    0.37
    海底
    0.37
    拓
    0.37
    POSITIVE LOGITS
    🙎
    0.43
    枴
    0.39
     griego
    0.38
    âmara
    0.37
     nasceu
    0.37
     fator
    0.37
     पढ़ी
    0.37
    واں
    0.37
    Equal
    0.36
    òng
    0.36
    Activations Density 0.000%

    No Known Activations