© 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. 18-GEMMASCOPE-TRANSCODER-16K
    7. 4636
    Prev
    Next
    INDEX
    Explanations

    adverbs and words signifying degree or qualification

    oai_token-act-pair · gemini-2.0-flash

    technical descriptions

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_18/width_16k/average_l0_13
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.18.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
    saraba
    -0.70
    AndEndTag
    -0.51
     protoimpl
    -0.50
    εύ
    -0.49
    XMLSchema
    -0.47
    AFX
    -0.46
     modellen
    -0.46
     Приступљено
    -0.46
     ModelExpression
    -0.46
    eness
    -0.46
    POSITIVE LOGITS
    windowFixed
    0.60
    ftagPool
    0.57
    Geographie
    0.56
    SharedDtor
    0.55
    ünstler
    0.52
     createSprite
    0.52
     kasarigan
    0.48
     ddelweddau
    0.48
     kohdetta
    0.48
     heapq
    0.47
    Activations Density 3.207%

    No Known Activations