© 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. 0-GEMMASCOPE-TRANSCODER-16K
    7. 7694
    Prev
    Next
    INDEX
    Explanations

    mentions of "levels" and "genes" especially in a scientific context

    oai_token-act-pair · gemini-2.0-flash

    levels

    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
    EDEFAULT
    -0.69
    ]$}
    -0.64
    daß
    -0.59
    andaag
    -0.59
    raszam
    -0.59
     ?',
    -0.57
    Atentamente
    -0.57
     Catawiki
    -0.57
    :-(
    -0.57
    — 
    -0.55
    POSITIVE LOGITS
    <bos>
    0.87
    Datuak
    0.70
     cepillo
    0.60
    ftagPool
    0.56
    IsContent
    0.55
    findpost
    0.55
    exitRule
    0.50
    rimid
    0.50
     spett
    0.50
    dicionado
    0.49
    Activations Density 0.970%

    No Known Activations