© 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. 14722
    Prev
    Next
    INDEX
    Explanations

    academic writing about linguistics and social science

    oai_token-act-pair · gemini-2.0-flash

    academic/research text

    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
    tvguidetime
    -0.68
    RRect
    -0.61
    ftagPool
    -0.60
    höhung
    -0.56
    ReusableCell
    -0.56
    __':
    -0.54
    hnia
    -0.53
    sonaro
    -0.52
    iläum
    -0.51
     Fold
    -0.51
    POSITIVE LOGITS
    पया
    0.56
     Organization
    0.52
    原始内容存档于
    0.52
    Organization
    0.52
     romana
    0.51
    XmlAccessorType
    0.50
    Lähteet
    0.50
    contextMenu
    0.49
     intervento
    0.48
     organization
    0.48
    Activations Density 16.529%

    No Known Activations