© 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. 4502
    Prev
    Next
    INDEX
    Explanations

    research paper results and comparing different methodologies

    oai_token-act-pair · gemini-2.0-flash

    that/those

    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
    Архівовано
    -0.53
    equalTo
    -0.51
    Примечания
    -0.50
     those
    -0.49
    ⓧ
    -0.48
    zwe
    -0.47
    ########.
    -0.47
     disponibilités
    -0.46
    ativement
    -0.45
    ValueStyle
    -0.44
    POSITIVE LOGITS
     دیکھیے
    0.64
     CreateTagHelper
    0.60
     sintético
    0.57
    kloped
    0.56
     nyelven
    0.56
     pierdas
    0.56
    MENAFN
    0.56
    VARIANT
    0.51
     Pinch
    0.51
    __":
    0.51
    Activations Density 21.166%

    No Known Activations