© 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. 24-GEMMASCOPE-TRANSCODER-16K
    7. 8296
    Prev
    Next
    INDEX
    Explanations

    words related to storytelling or events, specifically with a positive or excited tone

    oai_token-act-pair · gemini-2.0-flash

    unique words

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_24/width_16k/average_l0_37
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.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
     autorytatywna
    -0.58
    expandindo
    -0.54
     propOrder
    -0.53
     мәкал
    -0.52
     незавершена
    -0.51
     isComment
    -0.51
    IntoConstraints
    -0.50
     few
    -0.50
    SpringRunner
    -0.49
    ✭✭
    -0.49
    POSITIVE LOGITS
    phosa
    0.69
    ioutil
    0.59
     שוליים
    0.57
    rawDesc
    0.54
    terase
    0.54
    AlterField
    0.53
    agascar
    0.52
    ::-
    0.52
    tovat
    0.52
    rentices
    0.51
    Activations Density 15.303%

    No Known Activations