© 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. 2688
    Prev
    Next
    INDEX
    Explanations

    numbers and delimiters, often alongside extra spaces

    oai_token-act-pair · gemini-2.0-flash

    GPS coordinates

    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
    CONSE
    -0.50
     prezen
    -0.46
     []*
    -0.46
     neri
    -0.45
    Artik
    -0.44
    voa
    -0.44
    niad
    -0.43
    초
    -0.43
     domestic
    -0.43
    EmptyString
    -0.43
    POSITIVE LOGITS
    <bos>
    1.19
     beginnetje
    0.71
     ModelExpression
    0.69
     <<<<<<<<<<<<<<
    0.69
    ViewFeatures
    0.68
     utafitiHapana
    0.65
     ThemeData
    0.65
    izr
    0.64
    locene
    0.64
     Мексичка
    0.61
    Activations Density 3.036%

    No Known Activations