© 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. 0-GEMMASCOPE-TRANSCODER-16K
    7. 12340
    Prev
    Next
    INDEX
    Explanations

    the phrase "press release", which likely identifies documents of a certain type

    oai_token-act-pair · gemini-2.0-flash

    release

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_0/width_16k/average_l0_76
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.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
     незавершена
    -0.73
    DockStyle
    -0.62
     télévis
    -0.61
     Проци
    -0.61
     compétence
    -0.61
    enumii
    -0.60
    Czytaj
    -0.59
    aarrggbb
    -0.57
     nourriture
    -0.57
     étudi
    -0.56
    POSITIVE LOGITS
    original
    0.65
     Nothing
    0.57
     original
    0.57
    stination
    0.57
    至于
    0.57
    Nothing
    0.56
    MathML
    0.56
     stras
    0.54
    Apparently
    0.52
    ándole
    0.52
    Activations Density 0.110%

    No Known Activations