© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 23-GEMMASCOPE-TRANSCODER-16K
    7. 12075
    Prev
    Next
    INDEX
    Explanations

    words prefixed by "mis-", "in-", "com-", or individual Arabic characters

    oai_token-act-pair · gemini-2.0-flash

    foreign words

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_23/width_16k/average_l0_25
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.23.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
    UnusedPrivate
    -0.48
    рева
    -0.47
     chip
    -0.44
    HtmlAttribute
    -0.43
    umat
    -0.42
    entis
    -0.41
    rawDesc
    -0.41
     bad
    -0.40
     fore
    -0.40
     us
    -0.40
    POSITIVE LOGITS
     élector
    0.74
     bezeichneter
    0.69
     Efq
    0.67
     дописавши
    0.67
     يتيمه
    0.65
     iſt
    0.63
    anmoins
    0.63
     ſeveral
    0.63
     Мексичка
    0.63
     Monfieur
    0.63
    Activations Density 0.607%

    No Known Activations