© 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. 0-GEMMASCOPE-TRANSCODER-16K
    7. 11200
    Prev
    Next
    INDEX
    Explanations

    a mix of Danish words and phrases, particularly those that might be titles or headings

    oai_token-act-pair · gemini-2.0-flash

    ry or en

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_0/width_16k/average_l0_76
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.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
    GEBURTSDATUM
    -0.85
    Geplaatst
    -0.66
    resave
    -0.57
     concurrently
    -0.57
    Vidite
    -0.56
     defaultstate
    -0.56
    +#+#
    -0.53
    nocześnie
    -0.53
    rungsseite
    -0.52
    共に
    -0.52
    POSITIVE LOGITS
     Grado
    0.59
     Pring
    0.57
     $:$
    0.54
     Theſe
    0.53
     Angew
    0.52
     Wikiseite
    0.52
     ―――――
    0.52
     Sora
    0.51
    copg
    0.51
     ſome
    0.51
    Activations Density 0.161%

    No Known Activations