© 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. 47-GEMMASCOPE-2-TRANSCODER-262K
    7. 218172
    Prev
    Next
    INDEX
    Explanations

    scientific names

    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_47_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
     Mack
    1.01
     mackerel
    0.96
     M
    0.90
    Mack
    0.90
     mak
    0.81
     Mak
    0.76
     ম্যাক
    0.76
    Mak
    0.75
     막
    0.75
    막
    0.75
    POSITIVE LOGITS
    Gly
    0.51
     glycine
    0.49
    ॉर
    0.42
     Gly
    0.41
    ເທ
    0.41
    lge
    0.40
    gly
    0.39
     karn
    0.37
     hugs
    0.37
    SelfPermission
    0.37
    Activations Density 0.002%

    No Known Activations