© 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. 10367
    Prev
    Next
    INDEX
    Explanations

    mentions of "Amazon Kinesis Data Streams".

    oai_token-act-pair · gemini-2.0-flash

    Amazon AWS services

    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
    ArrowToggle
    -0.62
    enderror
    -0.59
     Dominus
    -0.56
    évaluateur
    -0.56
    Hochspringen
    -0.54
    asjonen
    -0.52
    esgue
    -0.52
    permum
    -0.51
     Schützen
    -0.51
     llev
    -0.50
    POSITIVE LOGITS
     CreateTagHelper
    0.65
     мәкал
    0.50
    Demografía
    0.50
     lenker
    0.47
    כנס
    0.45
    NotBlank
    0.43
    Quora
    0.43
    ump
    0.42
     ISNI
    0.42
    Ведь
    0.42
    Activations Density 4.337%

    No Known Activations