© 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. 9050
    Prev
    Next
    INDEX
    Explanations

    words, phrases or components of sentences in a variety of unrelated fields, that when considered individually suggest validation, confirmation or emphasis.

    oai_token-act-pair · gemini-2.0-flash

    code and modifications

    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
     Expanded
    -1.09
     amended
    -1.05
     expanded
    -1.04
     enhancement
    -1.00
     Expand
    -0.99
     expand
    -0.98
     revised
    -0.97
     modified
    -0.97
     adjusted
    -0.96
     upgraded
    -0.96
    POSITIVE LOGITS
    twimg
    0.81
    AndEndTag
    0.79
    AddTagHelper
    0.79
    ValueStyle
    0.74
     iprot
    0.61
    허
    0.59
     Roskov
    0.58
     noqa
    0.57
    StoryboardSegue
    0.56
    存于互联网档案馆
    0.54
    Activations Density 7.375%

    No Known Activations