© 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. 10483
    Prev
    Next
    INDEX
    Explanations

    LaTeX code for including figures

    oai_token-act-pair · gemini-2.0-flash

    }

    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
    niająca
    -0.79
     שוליים
    -0.78
    存于互联网档案馆
    -0.76
     समीक्षक
    -0.74
    rungsseite
    -0.74
    पया
    -0.74
    adaptiveStyles
    -0.72
     Мексичка
    -0.72
    numerusform
    -0.69
    +:+
    -0.69
    POSITIVE LOGITS
     arbete
    0.34
    %)
    0.34
     trouw
    0.33
     användas
    0.33
     ország
    0.32
    2
    0.32
    al
    0.31
    ++;
    0.31
     %
    0.31
    %
    0.30
    Activations Density 19.764%

    No Known Activations