© 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. 3238
    Prev
    Next
    INDEX
    Explanations

    words that could be used to describe art, especially visual art

    oai_token-act-pair · gemini-2.0-flash

    art and painting

    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
    ICom
    -0.55
    mentaires
    -0.53
    ]-'
    -0.50
     élas
    -0.50
    ]='\
    -0.49
    '}>
    -0.49
    }{#
    -0.48
     OMITTED
    -0.48
    )<\
    -0.48
     vastaan
    -0.47
    POSITIVE LOGITS
     Roskov
    0.66
    MLLoader
    0.60
    GOTREF
    0.59
    roek
    0.59
    WebMethod
    0.58
     nakalista
    0.57
    RTLU
    0.55
    Спасылкі
    0.55
     im
    0.55
     ri
    0.54
    Activations Density 2.221%

    No Known Activations