© 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. 5888
    Prev
    Next
    INDEX
    Explanations

    references to personal connections and negative feelings towards famous people or fictional characters.

    oai_token-act-pair · gemini-2.0-flash

    incomplete text with names

    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
     définiti
    -1.19
     fermés
    -1.18
     traités
    -1.15
     normaux
    -1.11
     automatiques
    -1.11
     démocr
    -1.11
     prêtres
    -1.10
     blessés
    -1.09
     scolaires
    -1.09
     découver
    -1.09
    POSITIVE LOGITS
    ­
    0.46
    fl
    0.45
    Â
    0.45
    fi
    0.44
    ¹
    0.43
    <bos>
    0.43
    â
    0.42
     ―
    0.42
    ’
    0.41
    ―
    0.40
    Activations Density 12.372%

    No Known Activations