© 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. 46-GEMMASCOPE-2-TRANSCODER-262K
    7. 233535
    Prev
    Next
    INDEX
    Explanations

    programming code

    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
    garakan
    0.41
     Sereth
    0.40
    libexec
    0.40
     பரபர
    0.40
     cybers
    0.39
     کنکریاں
    0.39
    笫
    0.38
    لیسی
    0.38
    鸷
    0.38
     mrt
    0.38
    POSITIVE LOGITS
     Process
    0.41
     O
    0.40
    ิว
    0.40
    IPA
    0.40
    Process
    0.40
    ail
    0.39
     utilize
    0.38
    Meaning
    0.38
    ピア
    0.38
    OP
    0.38
    Activations Density 0.003%

    No Known Activations