© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 51-GEMMASCOPE-2-TRANSCODER-262K
    7. 68769
    Prev
    Next
    INDEX
    Explanations

    Ram

    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_51_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
    channels
    0.45
    是的
    0.39
    Channels
    0.38
    臨
    0.38
     паз
    0.38
     pst
    0.37
    acyjnego
    0.37
    λει
    0.37
    mojo
    0.36
     fickle
    0.36
    POSITIVE LOGITS
    Թ
    0.40
     sourced
    0.40
    fontenc
    0.38
     কিছু
    0.38
     sourcing
    0.38
    筒
    0.38
     abstracted
    0.37
    posure
    0.36
     Chosen
    0.36
     traged
    0.36
    Activations Density 0.000%

    No Known Activations