© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 25-GEMMASCOPE-TRANSCODER-16K
    7. 11731
    Prev
    Next
    INDEX
    Explanations

    intensifiers such as "very" "same" and possessive pronouns such as "its" "our" and "the"

    oai_token-act-pair · gemini-2.0-flash

    its

    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
     very
    -3.17
    Very
    -3.00
     Very
    -2.92
    very
    -2.86
    VERY
    -2.34
     VERY
    -2.25
     très
    -2.11
     muy
    -2.09
     Très
    -1.70
     sehr
    -1.70
    POSITIVE LOGITS
    MENAFN
    0.59
    rrggbb
    0.57
    yntaxException
    0.56
    webElementXpaths
    0.56
    olge
    0.56
    Collections
    0.55
    MemoryWarning
    0.54
     EconPapers
    0.53
     CURIAM
    0.52
     communiquez
    0.52
    Activations Density 6.126%

    No Known Activations