© 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. 50-GEMMASCOPE-2-TRANSCODER-262K
    7. 130369
    Prev
    Next
    INDEX
    Explanations

    put

    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_50_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
    ದ್
    0.36
     переписи
    0.36
    झ्
    0.35
     Mars
    0.34
    ሳት
    0.33
    omone
    0.32
    ক্তি
    0.31
    蠶
    0.31
    ద్
    0.31
     budd
    0.30
    POSITIVE LOGITS
     put
    2.97
    Put
    2.80
     Put
    2.72
    put
    2.64
     putting
    2.52
     puts
    2.50
     PUT
    2.44
     Putting
    2.44
    Putting
    2.33
    PUT
    2.30
    Activations Density 0.098%

    No Known Activations