© 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. 8-GEMMASCOPE-TRANSCODER-16K
    7. 3352
    Prev
    Next
    INDEX
    Explanations

    words related to extinct crocodiles and the discovery or reporting of them

    oai_token-act-pair · gemini-2.0-flash

    land

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_8/width_16k/average_l0_52
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.8.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
    atung
    -0.51
    IFY
    -0.50
    ENTR
    -0.49
     need
    -0.48
     unlike
    -0.48
    orated
    -0.48
    ROP
    -0.47
    need
    -0.47
    typical
    -0.47
    скать
    -0.45
    POSITIVE LOGITS
     للمعارف
    0.81
    出版年
    0.75
     GenerationType
    0.73
     للاسماء
    0.70
    parsedMessage
    0.69
    bootstrapcdn
    0.68
    ftagPool
    0.66
     transfieras
    0.65
    GenerationType
    0.65
     незавершена
    0.63
    Activations Density 26.933%

    No Known Activations