© 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. 2-GEMMASCOPE-2-TRANSCODER-262K
    7. 112985
    Prev
    Next
    INDEX
    Explanations

    an/ada/ado/ancha/ad/za

    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_2_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
    ক
    1.27
    1.16
    و
    1.15
    ad
    1.11
    ง
    1.11
    da
    1.09
    人
    1.09
    يه
    1.08
    than
    1.02
    大脑
    1.02
    POSITIVE LOGITS
     fabriqu
    1.38
     увеличи
    1.20
    ૦
    1.19
     qualific
    1.16
     preocupaciones
    1.16
     conç
    1.11
     déprim
    1.10
    ᱐
    1.07
     vincul
    1.06
     chois
    1.05
    Activations Density 0.012%

    No Known Activations