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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-2B
    3. 25-GEMMASCOPE-TRANSCODER-16K
    4. 1066
    Prev
    Next
    INDEX
    Explanations

    words when quantifying and words to combine multiple concepts.

    oai_token-act-pair · gemini-2.0-flash

    auxiliary verbs

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_25/width_16k/average_l0_41
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.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
    .}
    -0.98
    .");
    -0.94
    .');
    -0.90
    .");
    
    -0.84
    .";
    -0.84
    .")
    -0.82
    .';
    -0.81
    ."]
    -0.79
    .);
    -0.79
    .')
    -0.78
    POSITIVE LOGITS
     is
    2.11
     has
    1.59
     are
    1.41
     was
    1.30
     isn
    1.16
     does
    1.11
     έχει
    1.02
     doesn
    1.02
     heeft
    0.98
     have
    0.96
    Activations Density 32.021%

    No Known Activations