© 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. 11450
    Prev
    Next
    INDEX
    Explanations

    the word "scope" and past tense verbs indicating a fall or decline

    oai_token-act-pair · gemini-2.0-flash

    programming scopes/falling out

    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
    <bos>
    -0.68
     opening
    -0.52
     scope
    -0.50
     fell
    -0.48
    InjectMocks
    -0.47
     
    -0.47
    ="@+
    -0.47
     falls
    -0.45
    juvant
    -0.45
    ddots
    -0.43
    POSITIVE LOGITS
     Roskov
    0.97
    tagHelperRunner
    0.90
    styleType
    0.89
    AutoField
    0.83
    ConstraintMaker
    0.77
     CreateTagHelper
    0.76
     doubtnut
    0.76
     JAXBElement
    0.75
    +:+
    0.74
    )}]{
    0.73
    Activations Density 0.834%

    No Known Activations