© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 3-GEMMASCOPE-TRANSCODER-16K
    7. 5355
    Prev
    Next
    INDEX
    Explanations

    discourse markers like "or", "but", instances of the verb "to be", and short words consisting of two or three letters

    oai_token-act-pair · gemini-2.0-flash

    Ou

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_3/width_16k/average_l0_54
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.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>
    -0.84
     bądź
    -0.69
    oder
    -0.66
     či
    -0.66
     ou
    -0.66
     nebo
    -0.63
    AddHtmlAttribute
    -0.59
    ImageContext
    -0.56
     oder
    -0.55
    aarrggbb
    -0.55
    POSITIVE LOGITS
    ]--;
    0.65
    duled
    0.61
    nthesis
    0.60
    antMatchers
    0.60
    enterOuterAlt
    0.60
    verifyException
    0.59
    ]++;
    0.58
    glise
    0.57
    ]='\
    0.57
    cedures
    0.56
    Activations Density 5.053%

    No Known Activations