© 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. 25-GEMMASCOPE-TRANSCODER-16K
    7. 4141
    Prev
    Next
    INDEX
    Explanations

    words related to human experiences, especially negative ones

    oai_token-act-pair · gemini-2.0-flash

    stories

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_25/width_16k/average_l0_41
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.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
     story
    -1.66
    story
    -1.45
     Story
    -1.38
    Story
    -1.34
     STORY
    -1.21
    STORY
    -1.11
     tale
    -0.91
     picture
    -0.90
     verhaal
    -0.81
    geschichte
    -0.75
    POSITIVE LOGITS
    Personensuche
    0.73
     Waray
    0.70
     ویکی‌پدیای
    0.65
    StructEnd
    0.57
    LookAnd
    0.56
    ราะ
    0.56
    raft
    0.53
    期刊论文
    0.52
    anski
    0.52
    Referensi
    0.51
    Activations Density 9.776%

    No Known Activations