© 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. 12-GEMMASCOPE-TRANSCODER-16K
    7. 8751
    Prev
    Next
    INDEX
    Explanations

    references to figures, listings and architectures

    oai_token-act-pair · gemini-2.0-flash

    figure

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_12/width_16k/average_l0_6
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.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
    Viitteet
    -0.56
     Winaray
    -0.49
    Hozzáférés
    -0.48
    милия
    -0.45
    @{
    -0.44
     deal
    -0.44
     Jwt
    -0.44
     riff
    -0.43
    Jew
    -0.42
    УДК
    -0.42
    POSITIVE LOGITS
     Theſe
    0.79
     Paglinawan
    0.77
     Monfieur
    0.76
     ویکی‌پدیا
    0.71
     Jefus
    0.71
     myſelf
    0.70
     betweenstory
    0.66
    يكب
    0.65
     becauſe
    0.65
     purpoſe
    0.65
    Activations Density 1.164%

    No Known Activations