© 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. 8441
    Prev
    Next
    INDEX
    Explanations

    sentences that include conflicting opinions or statements regarding who, what, when, where, or why

    oai_token-act-pair · gemini-2.0-flash

    Unspecified people

    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
    ↵
    -0.43
     
    -0.41
    太平
    -0.40
     Classic
    -0.38
     or
    -0.36
    ::
    -0.36
     Jefe
    -0.35
    сле
    -0.35
    Back
    -0.35
    :
    -0.34
    POSITIVE LOGITS
    IsContent
    0.89
    rungsseite
    0.87
     StringTokenizer
    0.84
    eleste
    0.79
     AssemblyCompany
    0.79
    LookAnd
    0.79
    Portale
    0.78
    UrlResolution
    0.77
     initComponents
    0.77
     AssemblyCulture
    0.77
    Activations Density 1.915%

    No Known Activations