© 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. 55-GEMMASCOPE-2-TRANSCODER-262K
    7. 54113
    Prev
    Next
    INDEX
    Explanations

    i

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_55_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
    !";
    0.43
    )";
    0.40
     बिफोर
    0.39
    ).}
    0.39
    。",
    0.38
    .";
    0.38
     .\
    0.38
    バース
    0.37
    Before
    0.37
     Before
    0.36
    POSITIVE LOGITS
     interface
    0.38
     inn
    0.36
     Interview
    0.36
    Bamboo
    0.35
    蠶
    0.35
    (()=>{
    0.35
     interview
    0.35
    με
    0.35
    SARS
    0.35
     Interface
    0.35
    Activations Density 0.003%

    No Known Activations