© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 24-GEMMASCOPE-TRANSCODER-16K
    7. 5321
    Prev
    Next
    INDEX
    Explanations

    words and phrases used in call to actions

    oai_token-act-pair · 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
    )++;
    -0.61
    XmlRootElement
    -0.60
    ofollow
    -0.59
    InvalidProtocol
    -0.56
     extranjera
    -0.55
    cherie
    -0.54
     starry
    -0.54
    eados
    -0.52
    ceq
    -0.52
    Lage
    -0.52
    POSITIVE LOGITS
    Portail
    0.63
     يتيمه
    0.59
     up
    0.58
    principalColumn
    0.56
     الرياضيه
    0.56
     AssemblyCompany
    0.53
    ərbaycan
    0.51
    Portale
    0.49
    istoitu
    0.49
    pushFollow
    0.47
    Activations Density 1.481%

    No Known Activations