© 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. 37-GEMMASCOPE-2-TRANSCODER-262K
    7. 200820
    Prev
    Next
    INDEX
    Explanations

    subjects followed by verbs

    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_37_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
    協会
    0.37
    fares
    0.37
    がお
    0.36
     గ
    0.35
    whose
    0.35
    }\|_{
    0.35
    <unused404>
    0.35
     دارای
    0.34
    )]$
    0.34
     மேல்
    0.34
    POSITIVE LOGITS
     resulted
    0.57
     realizada
    0.57
     realizadas
    0.55
     usada
    0.51
     lasts
    0.50
     berupa
    0.50
     realizados
    0.50
     effectués
    0.49
     occurred
    0.49
     occurring
    0.49
    Activations Density 0.026%

    No Known Activations