© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 7-GEMMASCOPE-TRANSCODER-16K
    7. 9558
    Prev
    Next
    INDEX
    Explanations

    language commonly found in academic papers, especially those about numerical methods and algorithms, and including citations, equations, and references to theorems.

    oai_token-act-pair · gemini-2.0-flash

    computational methods

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_7/width_16k/average_l0_70
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.7.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
    thereum
    -0.44
    Filmografie
    -0.44
    ティブ
    -0.42
     resident
    -0.42
    VID
    -0.40
     thinking
    -0.40
     maximum
    -0.39
    MethodManager
    -0.39
    LLES
    -0.38
    ิลป
    -0.38
    POSITIVE LOGITS
    rungsseite
    0.89
    ⓧ
    0.77
    webElementXpaths
    0.76
    éez
    0.70
    AnchorStyles
    0.68
    +#+#
    0.68
     дописавши
    0.67
     AssemblyCulture
    0.67
    kloped
    0.66
     nakalista
    0.66
    Activations Density 10.813%

    No Known Activations