© 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. 11074
    Prev
    Next
    INDEX
    Explanations

    text that appears to be from technical documentation, business documents, or academic papers

    oai_token-act-pair · gemini-2.0-flash

    research or technical docs

    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
     ſtate
    -0.98
     purpoſe
    -0.93
     Majefty
    -0.92
     cauſe
    -0.91
    ſelves
    -0.91
     itſelf
    -0.91
    ſelf
    -0.89
     quæ
    -0.88
     houſe
    -0.88
     greateſt
    -0.88
    POSITIVE LOGITS
     di
    0.41
     au
    0.36
     sem
    0.35
     Ne
    0.35
     sia
    0.35
    耘
    0.35
     tr
    0.34
    ().
    0.34
     El
    0.33
     ao
    0.33
    Activations Density 3.970%

    No Known Activations