© 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. 5726
    Prev
    Next
    INDEX
    Explanations

    job postings that provide hourly rates and working hours, especially those offering weekend or holiday work.

    oai_token-act-pair · gemini-2.0-flash

    Scheduling and hours

    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
    (!__
    -0.48
    Flesh
    -0.46
     inteligen
    -0.46
    UnknownFieldSet
    -0.46
    ochim
    -0.45
    yAxis
    -0.45
    ocardium
    -0.45
    ochet
    -0.45
     دیکھیے
    -0.45
    crisy
    -0.45
    POSITIVE LOGITS
    awtextra
    0.62
    httphttps
    0.58
    !*\
    0.57
     Италијани
    0.57
     Normdatei
    0.56
    styleType
    0.56
     makl
    0.56
     Mons
    0.56
    CloseOperation
    0.54
     Monro
    0.53
    Activations Density 7.026%

    No Known Activations