© 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. 4798
    Prev
    Next
    INDEX
    Explanations

    code snippets and delimiters

    oai_token-act-pair · gemini-2.0-flash

    code

    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
    AndEndTag
    -0.81
    styleType
    -0.77
     propOrder
    -0.74
     Roskov
    -0.71
    脚注の使い方
    -0.69
    Referencies
    -0.69
     esternos
    -0.68
     Efq
    -0.68
     дописавши
    -0.66
    ."</
    -0.66
    POSITIVE LOGITS
    )
    0.87
    ),
    0.82
    ).
    0.77
    ）
    0.77
    -
    0.72
    ')
    0.68
    -)
    0.67
    );
    0.65
    .)
    0.61
    7
    0.60
    Activations Density 8.319%

    No Known Activations