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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 22-GEMMASCOPE-TRANSCODER-16K
    7. 10425
    Prev
    Next
    INDEX
    Explanations

    code and numbers, occasionally activating on certain medical words

    oai_token-act-pair · gemini-2.0-flash

    Punctuation and numbers

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_22/width_16k/average_l0_15
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.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
    ⓧ
    -1.10
    Diweddarwch
    -1.07
    bootstrapcdn
    -1.06
    NameInMap
    -1.05
    SequentialGroup
    -1.04
     كومونز
    -0.99
     Efq
    -0.97
    ſelf
    -0.96
     houſe
    -0.96
     EconPapers
    -0.95
    POSITIVE LOGITS
    ,
    0.94
    ;
    0.56
    -
    0.55
     ,
    0.53
    (
    0.53
    7
    0.52
    0
    0.52
    2
    0.49
    3
    0.49
    5
    0.48
    Activations Density 9.121%

    No Known Activations