© 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. 17596
    Prev
    Next
    INDEX
    Explanations

    code examples

    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
     bowing
    0.27
     cors
    0.26
    )&
    0.25
     వై
    0.25
    }^{*}(
    0.24
     introspection
    0.24
     tyranny
    0.24
     Bridgewater
    0.23
     $*$
    0.23
     coerc
    0.23
    POSITIVE LOGITS
    copied
    0.32
    COPY
    0.32
     Copy
    0.30
    コピー
    0.29
     COPY
    0.29
     कॉपी
    0.28
     copied
    0.28
    复制
    0.28
     কপি
    0.27
     kop
    0.27
    Activations Density 0.035%

    No Known Activations