© 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. 24-GEMMASCOPE-TRANSCODER-16K
    7. 15779
    Prev
    Next
    INDEX
    Explanations

    a wide variety of non-English language fragments, plus date-related text

    oai_token-act-pair · gemini-2.0-flash

    Geographical regions

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_24/width_16k/average_l0_37
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.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
     snippetHide
    -0.72
    tvguidetime
    -0.63
     GoogleFonts
    -0.59
    })*/
    -0.58
     makeStyles
    -0.57
     RestTemplate
    -0.55
     utafitiHapana
    -0.55
    >");
    -0.55
    });*/
    -0.54
    enumi
    -0.52
    POSITIVE LOGITS
     engravings
    0.49
    קישורים
    0.48
    LookAnd
    0.47
     rebellion
    0.45
     oaths
    0.45
     coronation
    0.45
     justifying
    0.44
     accessibility
    0.44
    XmlAccessType
    0.44
     برس
    0.44
    Activations Density 0.294%

    No Known Activations