© 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. 428
    Prev
    Next
    INDEX
    Explanations

    Dutch texts which reference funding for scientific research

    oai_token-act-pair · gemini-2.0-flash

    Research and foreign text

    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
    WithIOException
    -0.69
     eigh
    -0.69
     Asiatic
    -0.69
     altitudes
    -0.65
    ValueStyle
    -0.65
     UNAM
    -0.64
     Cassini
    -0.64
     Moslem
    -0.63
    })();
    -0.63
     bituminous
    -0.63
    POSITIVE LOGITS
     preuves
    0.57
     mères
    0.57
     bocca
    0.53
     démocr
    0.52
     travailleurs
    0.50
     volantes
    0.50
    ruimte
    0.49
     caratteri
    0.49
    område
    0.49
     refroid
    0.48
    Activations Density 1.403%

    No Known Activations