© 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. 11458
    Prev
    Next
    INDEX
    Explanations

    HTML and Javascript code syntax and snippets, alongside mathematical symbols and expressions

    oai_token-act-pair · gemini-2.0-flash

    variations of the word 'value'

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

    value

    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
     mergeFrom
    -0.55
    ніципалі
    -0.54
    mybatisplus
    -0.52
    awaiter
    -0.52
    তথ্যসূত্র
    -0.50
     <<<<<<<<<<<<<<
    -0.48
     pungkasnya
    -0.48
     cref
    -0.48
    Leben
    -0.47
    Искәрмәләр
    -0.47
    POSITIVE LOGITS
     value
    1.80
    value
    1.50
     values
    1.44
     VALUE
    1.38
     Value
    1.30
     valu
    1.26
    VALUE
    1.20
     valore
    1.18
     Wert
    1.16
     VALUES
    1.16
    Activations Density 1.789%

    No Known Activations