© 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. 0-GEMMASCOPE-TRANSCODER-16K
    4. 7748
    Prev
    Next
    INDEX
    Explanations

    words ending in "ing", and sometimes picks up other short words with similar letter combinations.

    oai_token-act-pair · gemini-2.0-flash

    ING

    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
     **/
    
    -1.07
    ']))
    
    -0.91
    )|^{
    -0.90
    ViewFeatures
    -0.89
    ]';
    -0.89
    )";
    
    -0.86
    '},
    
    -0.86
     XNUMX
    -0.83
    '))
    
    -0.83
    :%.
    -0.82
    POSITIVE LOGITS
     aeropuerto
    0.58
     oreilles
    0.58
    gaver
    0.57
    ,
    0.56
     idéia
    0.55
     iesp
    0.54
     réputation
    0.54
     ziua
    0.54
     companhia
    0.53
     समीक्षक
    0.53
    Activations Density 1.106%

    No Known Activations