© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 12-GEMMASCOPE-TRANSCODER-16K
    7. 13476
    Prev
    Next
    INDEX
    Explanations

    code-related tokens that include numbers and specialized terms.

    oai_token-act-pair · gemini-2.0-flash

    code, configuration, file paths

    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
     متعلقه
    -0.59
     correctes
    -0.51
    ⓧ
    -0.50
    eqn
    -0.46
    tainen
    -0.42
    Jegyzetek
    -0.41
    InvalidProtocol
    -0.41
    ámicas
    -0.41
     movable
    -0.40
    itinéraire
    -0.40
    POSITIVE LOGITS
    findpost
    0.72
    躇
    0.62
     =&
    0.57
    <tfoot>
    0.57
     firebaseConfig
    0.56
    bbene
    0.56
    AsUp
    0.56
    brainly
    0.55
    ově
    0.55
     Biôgrafia
    0.54
    Activations Density 2.290%

    No Known Activations