© 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. 5715
    Prev
    Next
    INDEX
    Explanations

    words and phrases associated with personal experiences, possibly including proper nouns and informal language.

    oai_token-act-pair · gemini-2.0-flash

    uncommon or rare words

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

    multiple languages

    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
    +#+#
    -0.77
    #+#
    -0.68
    +#+
    -0.68
    saraba
    -0.66
     oprot
    -0.63
     فريبيس
    -0.57
    '][]
    -0.57
    jsxFileName
    -0.56
     Wendy
    -0.55
    ErrUnexpectedEOF
    -0.55
    POSITIVE LOGITS
     nahilalakip
    0.64
    windowFixed
    0.50
     which
    0.45
    alité
    0.44
    går
    0.44
     Infórmanos
    0.43
    getDatabase
    0.42
    Enlaces
    0.41
    ,
    0.41
     ra
    0.41
    Activations Density 0.838%

    No Known Activations