© 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. 2351
    Prev
    Next
    INDEX
    Explanations

    proper names of people and/or places

    oai_token-act-pair · gemini-2.0-flash

    Names

    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
    مصادر
    -0.73
    SharedCtor
    -0.64
     her
    -0.59
    reportWebVitals
    -0.59
    sbericht
    -0.56
    RegressionTest
    -0.52
    undef
    -0.51
     hard
    -0.51
     numerus
    -0.50
    ukone
    -0.50
    POSITIVE LOGITS
     bénévoles
    0.69
    RectangleBorder
    0.68
     picioare
    0.68
     démocr
    0.65
    rrggbb
    0.64
     république
    0.64
     espirituales
    0.64
     fuite
    0.64
     disposto
    0.63
     paroisse
    0.63
    Activations Density 1.668%

    No Known Activations