© 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. 12-GEMMASCOPE-TRANSCODER-16K
    7. 12340
    Prev
    Next
    INDEX
    Explanations

    hyphenated alphanumeric sequences within code

    oai_token-act-pair · gemini-2.0-flash

    code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_12/width_16k/average_l0_6
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.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
    expandindo
    -0.79
    Personendaten
    -0.67
    Искәрмәләр
    -0.66
    oredCriteria
    -0.64
    ]";
    -0.64
     تانيه
    -0.64
     كمان
    -0.64
    Viited
    -0.64
     endblock
    -0.63
    OrBuilder
    -0.62
    POSITIVE LOGITS
     selv
    0.49
    MUT
    0.46
    的前
    0.45
     conscience
    0.44
    queles
    0.44
    zyms
    0.44
    toupper
    0.43
    Dy
    0.43
     Keim
    0.43
    SAA
    0.42
    Activations Density 1.896%

    No Known Activations