© 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. 4-GEMMASCOPE-TRANSCODER-16K
    7. 2661
    Prev
    Next
    INDEX
    Explanations

    gibberish, possibly due to a bad translation

    oai_token-act-pair · gemini-2.0-flash

    portal

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_4/width_16k/average_l0_88
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.4.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
     a
    -0.54
     un
    -0.47
     is
    -0.45
    IRQn
    -0.41
    <eos>
    -0.41
     ir
    -0.40
     dem
    -0.40
    未
    -0.40
     vittoria
    -0.40
     de
    -0.40
    POSITIVE LOGITS
     <=",
    0.92
    AddTagHelper
    0.92
    OGND
    0.89
    IsContent
    0.88
     فريبيس
    0.88
     gynhyrchwyd
    0.87
     propOrder
    0.86
    تقاوى
    0.85
    UserScript
    0.84
    argout
    0.82
    Activations Density 5.347%

    No Known Activations