Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-2-2B
    3. 20-GEMMASCOPE-TRANSCODER-16K
    4. 14686
    Prev
    Next
    INDEX
    Explanations

    fractions and proportions, often involving "out of"

    oai_token-act-pair · gemini-2.0-flash

    proportions and statistics

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_20/width_16k/average_l0_11
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.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
     mergeFrom
    -0.77
     estekak
    -0.75
    MockBean
    -0.75
     للاسماء
    -0.72
     CreateTagHelper
    -0.69
     Италијани
    -0.66
     onResponse
    -0.65
     onPostExecute
    -0.64
     Waray
    -0.61
    LLocation
    -0.61
    POSITIVE LOGITS
    webElementGuid
    0.56
    {}
    
    0.41
    "]];
    0.40
    })`
    0.40
    }';
    0.39
    }")
    
    0.39
    }');
    0.39
    ILLES
    0.39
    migrationBuilder
    0.39
    lic
    0.39
    Activations Density 1.501%

    No Known Activations