© 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. 7-GEMMASCOPE-TRANSCODER-16K
    7. 12838
    Prev
    Next
    INDEX
    Explanations

    words related to time, measurement, and comparisons, particularly in medical or technical contexts.

    oai_token-act-pair · gemini-2.0-flash

    before and after

    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
    Kjelder
    -0.46
    *)&
    -0.45
     brands
    -0.45
    GenerationType
    -0.44
     Приступљено
    -0.42
     fragment
    -0.41
    chowa
    -0.40
    utnik
    -0.40
     rep
    -0.40
     modele
    -0.40
    POSITIVE LOGITS
     ſtate
    0.67
     vieilles
    0.61
     theſe
    0.61
    EDEFAULT
    0.60
     =======
    0.60
    netto
    0.60
     Reſ
    0.60
    IsMutable
    0.59
    InputBorder
    0.59
    setupUi
    0.58
    Activations Density 2.279%

    No Known Activations