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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 7-GEMMASCOPE-TRANSCODER-16K
    7. 9893
    Prev
    Next
    INDEX
    Explanations

    Java code syntax, specifically periods followed by single digit numbers and certain keywords like "net", "util", or "annotation".

    oai_token-act-pair · gemini-2.0-flash

    period

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_7/width_16k/average_l0_70
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.7.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
     disambiguazione
    -0.61
     ostavi
    -0.61
     препратки
    -0.60
    tvguidetime
    -0.58
     חיצוניים
    -0.56
     utafitiHapana
    -0.56
    oa̍t
    -0.54
     poveznice
    -0.54
     eventual
    -0.53
    StructEnd
    -0.53
    POSITIVE LOGITS
     purpoſe
    0.66
     RSSSF
    0.59
     myſelf
    0.57
     tongues
    0.54
     cauſe
    0.54
     reaſon
    0.53
     ſec
    0.52
     ſmall
    0.50
     faſt
    0.50
    PACKET
    0.50
    Activations Density 0.385%

    No Known Activations