© 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. 21-GEMMASCOPE-TRANSCODER-16K
    7. 5584
    Prev
    Next
    INDEX
    Explanations

    mathematical and/or programming text

    oai_token-act-pair · gemini-2.0-flash

    unusual or non-standard words and terms

    np_token-act-pair-logits · gpt-4o-mini
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_21/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.21.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
     Dickson
    -0.51
    rime
    -0.51
     Glob
    -0.51
     x
    -0.50
    x
    -0.49
     root
    -0.49
    itoneal
    -0.47
     Flanagan
    -0.47
     endogenous
    -0.47
    tuce
    -0.47
    POSITIVE LOGITS
    Хьажоргаш
    0.72
     referrerpolicy
    0.72
    Hozzáférés
    0.70
    OrBuilder
    0.62
    tvguidetime
    0.61
    istoitu
    0.60
    Vidite
    0.59
    didSet
    0.59
    DMETHOD
    0.58
    `,
    0.57
    Activations Density 6.142%

    No Known Activations