© 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
    2. Gemma-2-2B
    3. 12-GEMMASCOPE-TRANSCODER-16K
    4. 12988
    Prev
    Next
    INDEX
    Explanations

    equations or mathematical expressions

    oai_token-act-pair · gemini-2.0-flash

    Zero and infinity

    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
     AssemblyCompany
    -0.94
     متعلقه
    -0.91
    OGND
    -0.82
    
    -0.82
    Personensuche
    -0.82
     itſelf
    -0.80
     myſelf
    -0.79
    ]`
    -0.77
     auffi
    -0.77
     ſind
    -0.77
    POSITIVE LOGITS
    .
    0.54
    ↵
    0.51
    ConstraintMaker
    0.50
     setuptools
    0.49
     <<<<<<<<<<<<<<
    0.48
     —
    0.47
     or
    0.45
    —
    0.45
    ↵↵
    0.44
    <strong>
    0.43
    Activations Density 3.781%

    No Known Activations