© 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. 201377
    Prev
    Next
    INDEX
    Explanations

    greeting to meet you

    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
     HAVING
    0.47
     Having
    0.47
    Having
    0.45
    having
    0.44
     having
    0.43
     ayant
    0.42
    Versions
    0.41
    谬
    0.41
     Someone
    0.39
     jemand
    0.38
    POSITIVE LOGITS
    ),]),
    0.44
    ண்ண
    0.38
    䏹
    0.38
     joining
    0.38
     voltam
    0.38
     })),
    0.37
    wise
    0.37
    Wise
    0.37
     quitting
    0.36
     Participate
    0.36
    Activations Density 0.004%

    No Known Activations