© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 25-GEMMASCOPE-TRANSCODER-16K
    7. 2504
    Prev
    Next
    INDEX
    Explanations

    complex sentences with multiple clauses and emotional or physical reactions within dialog-heavy text.

    oai_token-act-pair · gemini-2.0-flash

    Narrative 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
    TagMode
    -0.89
    MigrationBuilder
    -0.80
    Autoritní
    -0.73
    Sucesor
    -0.65
     незавершена
    -0.64
    LookAnd
    -0.63
     defaultstate
    -0.63
     المعيارى
    -0.63
     الرياضيه
    -0.63
    Билгалдахарш
    -0.63
    POSITIVE LOGITS
    Salta
    0.54
     muñecas
    0.47
     borboleta
    0.46
    signup
    0.46
    turma
    0.45
    revalidate
    0.45
     difesa
    0.45
    fendi
    0.44
    وفاته
    0.44
     starb
    0.44
    Activations Density 3.812%

    No Known Activations