© 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. 24-GEMMASCOPE-TRANSCODER-16K
    7. 13619
    Prev
    Next
    INDEX
    Explanations

    a combination of math equations, code snippets, and times

    oai_token-act-pair · gemini-2.0-flash

    code and symbols

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_24/width_16k/average_l0_37
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.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
     Ts
    -0.90
     Ip
    -0.82
     Cs
    -0.79
     Ss
    -0.79
     Ai
    -0.78
     Uk
    -0.78
     Ls
    -0.78
     Os
    -0.75
     Mw
    -0.75
     Tc
    -0.75
    POSITIVE LOGITS
     nakalista
    0.77
    GEBURTSDATUM
    0.75
    OGND
    0.69
    featureID
    0.68
     AssemblyTitle
    0.63
    NullException
    0.61
     snippetHide
    0.60
    forChild
    0.60
    mobileqq
    0.59
    esModule
    0.58
    Activations Density 9.843%

    No Known Activations