© 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. 8945
    Prev
    Next
    INDEX
    Explanations

    words indicating steps in a process, subjective opinion, or examples

    oai_token-act-pair · gemini-2.0-flash

    simply

    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
    Lugares
    -0.54
    BindView
    -0.47
    urile
    -0.46
     Feder
    -0.46
    ração
    -0.45
    CreateModel
    -0.45
    otella
    -0.44
    scriptId
    -0.42
    FIB
    -0.41
    LUT
    -0.41
    POSITIVE LOGITS
     simply
    2.72
    simply
    2.53
    Simply
    2.31
     Simply
    2.30
     simplemente
    2.06
     simplesmente
    2.05
     simplement
    2.02
     semplicemente
    1.97
     merely
    1.74
     просто
    1.63
    Activations Density 10.153%

    No Known Activations