© 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. 6604
    Prev
    Next
    INDEX
    Explanations

    mentions of specific terms or acronyms used predominantly in technical scientific writing

    oai_token-act-pair · gemini-2.0-flash

    Scientific papers

    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
     PSM
    -1.29
     CPM
    -1.28
     CSM
    -1.28
     RCP
    -1.28
     CSP
    -1.28
     CPC
    -1.27
     CFS
    -1.27
     WPS
    -1.24
     PPS
    -1.24
     CPS
    -1.24
    POSITIVE LOGITS
    tagHelperRunner
    0.49
    SourceChecksum
    0.47
     opérateur
    0.46
    ContentAlignment
    0.45
     MANUFACTURING
    0.44
    windowFixed
    0.43
    SerializedSize
    0.43
     vaksinasi
    0.42
     pinjaman
    0.42
     AUTOR
    0.41
    Activations Density 4.903%

    No Known Activations