© 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. 23-GEMMASCOPE-TRANSCODER-16K
    7. 11005
    Prev
    Next
    INDEX
    Explanations

    snippets of C code including standard input/output error handling, file descriptors, and potentially array size validation.

    oai_token-act-pair · gemini-2.0-flash

    say "<"

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_23/width_16k/average_l0_25
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.23.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
    脚注の使い方
    -0.62
    :✨
    -0.57
     >
    -0.56
    /***/
    -0.55
    }>
    -0.55
    >>
    -0.55
     }}>
    -0.54
     (>
    -0.54
     الحره
    -0.53
     '>
    -0.52
    POSITIVE LOGITS
     <
    1.29
    <
    1.23
     below
    1.13
    )<
    1.08
    }<
    1.01
    below
    1.01
    !<
    0.98
    .<
    0.94
     Below
    0.94
    ]<
    0.94
    Activations Density 4.658%

    No Known Activations