© 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. 24-GEMMASCOPE-TRANSCODER-16K
    7. 11572
    Prev
    Next
    INDEX
    Explanations

    language about satellites, especially in the context of weather or climate monitoring

    oai_token-act-pair · gemini-2.0-flash

    Foreign words

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_24/width_16k/average_l0_37
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.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
    DockStyle
    -0.73
    expandindo
    -0.70
    tagHelperRunner
    -0.64
    nonatomic
    -0.60
     GenerationType
    -0.60
    venido
    -0.56
    enumi
    -0.54
    TextSpan
    -0.53
    __*/
    -0.52
    žiť
    -0.51
    POSITIVE LOGITS
    Cyfeiriadau
    0.61
     UnityEditor
    0.51
    Manbalar
    0.50
    각주
    0.49
    Formation
    0.49
     autorytatywna
    0.49
     Formations
    0.49
    TestingModule
    0.48
    cyjnych
    0.48
    riter
    0.48
    Activations Density 3.879%

    No Known Activations