© 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. 1025
    Prev
    Next
    INDEX
    Explanations

    code-related keywords

    oai_token-act-pair · gemini-2.0-flash

    Block

    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
    principalTable
    -0.56
    webElementGuid
    -0.51
    ndice
    -0.51
     <<"
    -0.46
    脚注の使い方
    -0.46
     Италијани
    -0.45
    Cyfarwyddwr
    -0.45
     shut
    -0.45
    TintMode
    -0.44
    Itoa
    -0.44
    POSITIVE LOGITS
     block
    0.60
     endblock
    0.58
    Block
    0.58
     blocks
    0.57
     Block
    0.57
    block
    0.57
     Blocks
    0.55
    ReusableCell
    0.55
    complexType
    0.54
     BLOCK
    0.53
    Activations Density 5.952%

    No Known Activations