© 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. 4-GEMMASCOPE-TRANSCODER-16K
    7. 11928
    Prev
    Next
    INDEX
    Explanations

    mentions of insanity, death, or cessation of business

    oai_token-act-pair · gemini-2.0-flash

    Mental state or business

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_4/width_16k/average_l0_88
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.4.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
    FunctionFlags
    -0.63
    XmlAccessType
    -0.62
    ntö
    -0.59
    enterOuterAlt
    -0.56
    RSpec
    -0.56
    ագրություններ
    -0.52
     hänen
    -0.52
    Personendaten
    -0.52
    قایناق‌لار
    -0.51
    LookAnd
    -0.50
    POSITIVE LOGITS
    rrggbb
    0.65
     getApplication
    0.60
     Hidup
    0.59
     getPosition
    0.59
     humaine
    0.58
    azar
    0.56
     getType
    0.56
    coda
    0.55
     iterable
    0.55
     Lengkap
    0.55
    Activations Density 1.777%

    No Known Activations