© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 23-GEMMASCOPE-2-TRANSCODER-262K
    7. 152204
    Prev
    Next
    INDEX
    Explanations

    more importantly,

    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
     techn
    0.37
     ελλην
    0.35
     bitterness
    0.35
     tule
    0.35
     hizmet
    0.35
    彝
    0.35
     bitter
    0.35
     curl
    0.34
     paralysie
    0.34
     lutte
    0.34
    POSITIVE LOGITS
    জিও
    0.32
     Bahan
    0.32
     junto
    0.31
    Qaeda
    0.31
     BH
    0.30
     نسبت
    0.30
     відбувається
    0.30
    🚺
    0.30
    囟
    0.30
     indicated
    0.30
    Activations Density 0.003%

    No Known Activations