© 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. 24-GEMMASCOPE-TRANSCODER-16K
    7. 12464
    Prev
    Next
    INDEX
    Explanations

    periods, the letter i, along with some numbers and other symbols likely from code

    oai_token-act-pair · gemini-2.0-flash

    Code and file paths

    np_max-act-logits · 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
    .
    -1.52
    .}
    -1.28
    .")
    -1.27
    .”.
    -1.26
    .'.
    -1.24
    .".
    -1.23
    .\"
    -1.23
    .")
    -1.22
    .
    -1.21
    .»
    -1.20
    POSITIVE LOGITS
    ↵↵
    0.65
    <eos>
    0.53
    ↵
    0.52
    ↵↵↵
    0.49
    </td>
    0.45
    :
    0.45
    ,
    0.44
    </h2>
    0.43
    </h6>
    0.40
    </code>
    0.40
    Activations Density 2.679%

    No Known Activations