© 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. 11-GEMMASCOPE-2-TRANSCODER-262K
    7. 40082
    Prev
    Next
    INDEX
    Explanations

    So,

    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_11_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
     that
    0.41
     concerne
    0.38
     însă
    0.38
     kay
    0.38
    tss
    0.36
     relish
    0.36
    েক্টর
    0.36
    ஐ
    0.36
     reduzir
    0.35
     bloke
    0.35
    POSITIVE LOGITS
    arán
    0.33
    urig
    0.33
     Ztg
    0.32
    ос
    0.32
     CryptoJS
    0.32
    anan
    0.31
    op
    0.31
    ocf
    0.31
    il
    0.31
    eqref
    0.30
    Activations Density 0.007%

    No Known Activations