Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-2-2B
    3. 21-GEMMASCOPE-TRANSCODER-16K
    4. 11241
    Prev
    Next
    INDEX
    Explanations

    positive and enthusiastic language and sentiment

    oai_token-act-pair · gemini-2.0-flash

    words related to positive experiences or emotions

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

    prepositions

    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
    PhysRevD
    -0.63
     conseguenza
    -0.62
     MutableLiveData
    -0.60
     portée
    -0.58
     réguli
    -0.56
     prêtres
    -0.56
     mû
    -0.56
     tendenza
    -0.56
     préférable
    -0.56
    ArgsConstructor
    -0.56
    POSITIVE LOGITS
     laughter
    0.66
     activity
    0.57
     beauty
    0.53
     laughs
    0.53
     الاطلاع
    0.52
     adventure
    0.52
     prosperity
    0.51
     drama
    0.51
    InputLabel
    0.50
     absurdity
    0.50
    Activations Density 2.554%

    No Known Activations