© 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
    2. Gemma-2-2B
    3. 21-GEMMASCOPE-TRANSCODER-16K
    4. 5521
    Prev
    Next
    INDEX
    Explanations

    initial letters appearing in the text

    oai_token-act-pair · gemini-2.0-flash

    specific data structures or identifiers

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

    Web forum posts

    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
    ,
    -0.79
     to
    -0.72
     in
    -0.66
     
    -0.64
     that
    -0.63
     O
    -0.62
     a
    -0.61
     with
    -0.60
     on
    -0.60
    -
    -0.60
    POSITIVE LOGITS
     Efq
    1.05
    Personendaten
    1.02
     doubtnut
    1.01
     itſelf
    1.00
    RegistryLite
    1.00
     ModelExpression
    0.99
    <unused14>
    0.97
    <unused23>
    0.97
    <unused8>
    0.97
    <pad>
    0.97
    Activations Density 0.666%

    No Known Activations