© 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. 5678
    Prev
    Next
    INDEX
    Explanations

    hexadecimal numbers that start with "0x7"

    oai_token-act-pair · gemini-2.0-flash

    specific identifiers or keywords in code

    np_token-act-pair-logits · gpt-4o-mini

    7

    np_max-act-logits · gemini-2.0-flash
    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
    orithm
    -0.59
    formatics
    -0.57
    pung
    -0.55
    mación
    -0.52
    icap
    -0.52
    ]--;
    -0.52
    באנגלית
    -0.51
    vass
    -0.51
     Filed
    -0.50
    igenous
    -0.50
    POSITIVE LOGITS
    LookAnd
    0.65
    windowFixed
    0.60
    UrlResolution
    0.57
     pinulongan
    0.56
    ✨:
    0.54
    TagMode
    0.54
    #+#
    0.54
     estimés
    0.53
     Idiot
    0.51
     nahilalakip
    0.50
    Activations Density 0.851%

    No Known Activations