© 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
    3. Gemma-2-2B
    5. 0-GEMMASCOPE-TRANSCODER-16K
    7. 5618
    Prev
    Next
    INDEX
    Explanations

    mentions of something being "based" on something else, or things being "among" a group of things

    oai_token-act-pair · gemini-2.0-flash

    Description or opinion

    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
    <bos>
    -0.71
    __":
    -0.68
    :✨
    -0.66
    __':
    -0.63
     okuyayım
    -0.59
    windowFixed
    -0.57
     }));
    -0.57
    ].)
    -0.56
    ⓧ
    -0.56
    %
    -0.54
    POSITIVE LOGITS
     summarised
    0.80
     organisers
    0.80
     learnt
    0.80
     criticised
    0.79
     Travellers
    0.79
     enquiries
    0.78
     apologised
    0.78
     standardised
    0.77
     finalised
    0.77
    trav
    0.77
    Activations Density 1.213%

    No Known Activations