© 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. 19-GEMMASCOPE-TRANSCODER-16K
    7. 8722
    Prev
    Next
    INDEX
    Explanations

    words used to argue for or against something,

    oai_token-act-pair · gemini-2.0-flash

    at

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_19/width_16k/average_l0_12
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.19.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
    Diwedd
    -0.69
    ^(@)
    -0.68
    olesale
    -0.67
     fubject
    -0.67
    StoryboardSegue
    -0.66
    ✨:
    -0.66
     Normdatei
    -0.66
    TRIBUN
    -0.65
    __*/
    -0.64
    vician
    -0.63
    POSITIVE LOGITS
     validamos
    0.41
    jede
    0.40
    had
    0.40
    an
    0.40
    si
    0.40
    io
    0.38
    us
    0.38
    ion
    0.38
     đối
    0.38
    以此
    0.38
    Activations Density 10.193%

    No Known Activations