© 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. 46-GEMMASCOPE-2-TRANSCODER-262K
    7. 67754
    Prev
    Next
    INDEX
    Explanations

    forms of "to be"

    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_46_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
     possesses
    0.40
     possess
    0.38
    resse
    0.36
     esempl
    0.36
    ökk
    0.36
    )";
    0.36
    ˶
    0.36
    
    0.35
    拿起
    0.35
    居
    0.35
    POSITIVE LOGITS
    猬
    0.41
     buena
    0.41
     buon
    0.40
     delegate
    0.38
    툼
    0.38
     good
    0.37
     Imagine
    0.37
     चांग
    0.37
     τό
    0.37
     méthod
    0.37
    Activations Density 0.007%

    No Known Activations