© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 22-GEMMASCOPE-TRANSCODER-16K
    7. 9992
    Prev
    Next
    INDEX
    Explanations

    articles in the text

    oai_token-act-pair · gemini-2.0-flash

    Technical discussions

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_22/width_16k/average_l0_15
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.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
    V
    -0.44
     mon
    -0.43
    v
    -0.42
    ّ
    -0.41
     stessi
    -0.41
    /
    -0.40
     v
    -0.40
    Aktualisiert
    -0.40
    ד
    -0.40
    actual
    -0.40
    POSITIVE LOGITS
     ProtoMessage
    0.94
    __':
    0.90
    ]--;
    0.90
    ,:);
    0.90
     sympy
    0.86
    %");
    0.86
    __":
    0.84
    ształ
    0.83
    
    0.80
     ReSharper
    0.79
    Activations Density 4.108%

    No Known Activations