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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 2-GEMMASCOPE-TRANSCODER-16K
    7. 11082
    Prev
    Next
    INDEX
    Explanations

    code snippets in languages like Javascript, HTML, or Java that contain operators, strings, and variable names

    oai_token-act-pair · gemini-2.0-flash

    spanish articles

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_2/width_16k/average_l0_49
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.2.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
    itudinal
    -0.60
     Hic
    -0.57
     STC
    -0.54
     SRM
    -0.53
    SRM
    -0.52
     MCI
    -0.51
     kule
    -0.50
    almaz
    -0.50
     nocturnal
    -0.49
     Pulaski
    -0.49
    POSITIVE LOGITS
    <bos>
    1.12
     them
    0.83
     themselves
    0.76
     him
    0.76
    Personensuche
    0.68
     himself
    0.67
    reactstrap
    0.66
    OGND
    0.65
    __":
    0.64
    __":
    0.64
    Activations Density 0.339%

    No Known Activations