© 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. 4-GEMMASCOPE-TRANSCODER-16K
    7. 14008
    Prev
    Next
    INDEX
    Explanations

    something to do with following instructions.

    oai_token-act-pair · gemini-2.0-flash

    Instructions

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_4/width_16k/average_l0_88
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.4.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
    <bos>
    -1.23
     دیکھیے
    -0.61
     your
    -0.59
    RegressionTest
    -0.57
     '\\;'
    -0.56
    thâu
    -0.54
    хьтан
    -0.54
     noDo
    -0.52
     yourself
    -0.50
    IUrlHelper
    -0.50
    POSITIVE LOGITS
    +#+
    0.63
    LayoutStyle
    0.58
     MyBatis
    0.54
    vice
    0.52
    InputBorder
    0.50
    ratos
    0.49
    ElementException
    0.49
    selig
    0.48
     ArrayAdapter
    0.48
     repro
    0.48
    Activations Density 1.026%

    No Known Activations