© 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
    3. Gemma-2-2B
    5. 24-GEMMASCOPE-TRANSCODER-16K
    7. 8532
    Prev
    Next
    INDEX
    Explanations

    prefixes like "anti-", "pro-", "co-" and "multi-", especially those found in medical/scientific contexts; it also looks for terms relating to malabsorption, muscles and adipose tissue, as well as carboxymethyl and hydroxyethyl cellulose.

    oai_token-act-pair · gemini-2.0-flash

    scientific/technical studies

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_24/width_16k/average_l0_37
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.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
     supérieurs
    -0.49
     }));
    -0.42
     }$
    -0.41
     pantaloni
    -0.38
     »)
    -0.36
    Http
    -0.36
     pulito
    -0.35
     }}}
    -0.35
    Geo
    -0.35
     ");
    -0.35
    POSITIVE LOGITS
    DeleteBehavior
    1.03
    parsedMessage
    0.94
    jsxFileName
    0.89
    contentLoaded
    0.89
    TemporalType
    0.88
     متعلقه
    0.87
     ComVisible
    0.84
    GEBURTSDATUM
    0.83
    awtextra
    0.81
     betweenstory
    0.81
    Activations Density 13.697%

    No Known Activations