© 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. 24-GEMMASCOPE-TRANSCODER-16K
    7. 8859
    Prev
    Next
    INDEX
    Explanations

    words related to legal obligations pertaining to information requests, beneficiaries, and trustees

    oai_token-act-pair · gemini-2.0-flash

    Legal, policies, obligations

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_24/width_16k/average_l0_37
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.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
    Diwedd
    -0.84
    OGND
    -0.77
     Roskov
    -0.76
    WebElementEntity
    -0.76
    featureID
    -0.75
     BIBSYS
    -0.75
    setVerticalGroup
    -0.74
    цездатний
    -0.72
    windowFixed
    -0.69
    unknownFields
    -0.67
    POSITIVE LOGITS
     Pesca
    0.47
    })()
    0.46
     Parkway
    0.45
     e
    0.43
     i
    0.43
     lī
    0.42
    runOnUiThread
    0.42
     ✭✭
    0.42
     navegando
    0.41
     tío
    0.41
    Activations Density 13.842%

    No Known Activations