© 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. 21-GEMMASCOPE-TRANSCODER-16K
    7. 10068
    Prev
    Next
    INDEX
    Explanations

    code snippets related to random number generation

    oai_token-act-pair · gemini-2.0-flash

    code-related keywords in programming

    np_token-act-pair-logits · gpt-4o-mini

    Randomness and code generation

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_21/width_16k/average_l0_13
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.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
    出版年
    -0.56
    requestCode
    -0.56
    transQ
    -0.55
    invokeLater
    -0.54
    ChildScrollView
    -0.51
    RegistryLite
    -0.49
    migrationBuilder
    -0.49
    AndEndTag
    -0.48
    CastException
    -0.47
     ErrIntOverflow
    -0.47
    POSITIVE LOGITS
    Nuorodos
    0.55
    gwt
    0.54
    ⁩
    0.54
    findpost
    0.52
     Sore
    0.51
     sumpay
    0.51
    ÉS
    0.50
    IGAN
    0.50
    ECONDS
    0.50
     }}"
    0.49
    Activations Density 0.536%

    No Known Activations