© 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. 864
    Prev
    Next
    INDEX
    Explanations

    medical research or terminology.

    oai_token-act-pair · gemini-2.0-flash

    scientific chemical studies

    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
    ]")]
    -0.69
    ActionPerformed
    -0.62
    enumi
    -0.61
    MockMvc
    -0.60
     esternos
    -0.57
    MergeFrom
    -0.57
    Aholisi
    -0.56
    __":
    -0.55
     yii
    -0.55
     useSelector
    -0.54
    POSITIVE LOGITS
    rungsseite
    0.72
    spunkt
    0.47
     esterni
    0.46
    ToBounds
    0.45
     ролях
    0.44
    Addo
    0.43
     Règlement
    0.42
     getSource
    0.42
    googleapis
    0.41
    AutoresizingMask
    0.41
    Activations Density 10.543%

    No Known Activations