© 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. 8514
    Prev
    Next
    INDEX
    Explanations

    code

    oai_token-act-pair · gemini-2.0-flash

    C code snippets

    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
    Hochspringen
    -0.86
     estekak
    -0.85
    GraphicsUnit
    -0.79
     متعلقه
    -0.78
    Източници
    -0.75
     utafitiHapana
    -0.74
     AssemblyCompany
    -0.73
     CreateTagHelper
    -0.72
    AddHtmlAttribute
    -0.72
    richTextPanel
    -0.71
    POSITIVE LOGITS
    prg
    0.51
    Pkt
    0.50
    PDU
    0.48
    Hdr
    0.47
    Dst
    0.45
    Drv
    0.45
    svc
    0.45
    Udp
    0.44
    drv
    0.44
    spc
    0.43
    Activations Density 14.846%

    No Known Activations