© 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-2-2B
    5. 22-GEMMASCOPE-TRANSCODER-16K
    7. 4619
    Prev
    Next
    INDEX
    Explanations

    the prefix "Ne"

    oai_token-act-pair · gemini-2.0-flash

    Ne

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_22/width_16k/average_l0_15
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.ln2.hook_normalized
    Architecture
    jumprelu_transcoder
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     المعيارى
    -0.63
    BagLayout
    -0.62
     kasarigan
    -0.59
    rungsseite
    -0.57
    EDEFAULT
    -0.56
    forsk
    -0.56
    sertations
    -0.55
    jsdelivr
    -0.55
    ungu
    -0.54
    adaptiveStyles
    -0.54
    POSITIVE LOGITS
     InputDecoration
    0.56
     dAtA
    0.53
     pleaſure
    0.52
     purpoſe
    0.51
     Diſ
    0.43
     وتسجيلات
    0.43
     Majefty
    0.43
     Anſ
    0.43
     חיצוניים
    0.42
     greateſt
    0.42
    Activations Density 0.596%

    No Known Activations