© 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. 67957
    Prev
    Next
    INDEX
    Explanations

    published

    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
    write
    0.40
    prite
    0.37
    hdfs
    0.37
    evident
    0.36
    plaintext
    0.35
    备
    0.35
    brewer
    0.35
    ㍉
    0.35
     કરાવ
    0.34
     ASSEM
    0.34
    POSITIVE LOGITS
     published
    2.66
     Published
    2.42
    published
    2.34
    Published
    2.33
     publicada
    2.05
     publicado
    2.02
     publicados
    1.95
     опубликован
    1.88
     pubblicato
    1.87
     publié
    1.82
    Activations Density 0.116%

    No Known Activations