© 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. 11621
    Prev
    Next
    INDEX
    Explanations

    the names of people, especially in academic settings, mentioning grants, or water plants

    oai_token-act-pair · gemini-2.0-flash

    ka

    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
     ostavi
    -0.56
     ſhould
    -0.51
     Urbano
    -0.46
    anskje
    -0.46
    })));
    -0.44
     uſe
    -0.43
     Monfieur
    -0.43
    nyttet
    -0.43
     ninjago
    -0.43
     muſt
    -0.42
    POSITIVE LOGITS
    GEBURTSDATUM
    0.85
    +#+#
    0.78
    脚注の使い方
    0.75
     autorytatywna
    0.74
    WriteTagHelper
    0.74
     صوتيه
    0.72
     дописавши
    0.70
    StoreMessageInfo
    0.70
     ویکی‌پدیا
    0.69
    DockStyle
    0.67
    Activations Density 1.571%

    No Known Activations