© 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
    2. Gemma-2-2B
    3. 25-GEMMASCOPE-TRANSCODER-16K
    4. 10558
    Prev
    Next
    INDEX
    Explanations

    quotes attributed to a speaker, with special attention to those in the business world, that contain opinions or assertions, negative experiences, and large numbers.

    oai_token-act-pair · gemini-2.0-flash

    quotation mark

    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
    "]];
    -0.69
    )}</
    -0.69
    "];
    
    -0.68
    ]:
    
    -0.67
    "]]
    -0.67
    **/
    
    -0.64
    ":
    
    -0.63
    ]**
    -0.63
    ."</
    -0.63
    "])
    
    -0.62
    POSITIVE LOGITS
    Their
    0.77
    their
    0.76
     Their
    0.71
    were
    0.66
    Who
    0.65
     whoſe
    0.63
    are
    0.63
    Are
    0.63
    per
    0.62
     Siapa
    0.62
    Activations Density 9.004%

    No Known Activations