© 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. 25-GEMMASCOPE-TRANSCODER-16K
    7. 8072
    Prev
    Next
    INDEX
    Explanations

    present tense verbs relating to intent or urging

    oai_token-act-pair · gemini-2.0-flash

    to

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_25/width_16k/average_l0_41
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.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
    </thead>
    -0.57
     continúas
    -0.57
     հղումներ
    -0.55
    MigrationBuilder
    -0.52
     oprot
    -0.52
    OGND
    -0.46
    abestanden
    -0.46
    IBarButtonItem
    -0.45
    webElementXpaths
    -0.45
    ArgumentParser
    -0.44
    POSITIVE LOGITS
     get
    1.99
     gotten
    1.82
     got
    1.82
     getting
    1.78
     gets
    1.77
    get
    1.68
     Getting
    1.64
     Get
    1.63
    getting
    1.61
    Getting
    1.59
    Activations Density 3.348%

    No Known Activations