© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 7-GEMMASCOPE-TRANSCODER-16K
    7. 12095
    Prev
    Next
    INDEX
    Explanations

    words pertaining to software, coding, and data analysis.

    oai_token-act-pair · gemini-2.0-flash

    code and systems

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_7/width_16k/average_l0_70
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.7.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
    WithIOException
    -0.85
    kháu
    -0.72
     препратки
    -0.71
     tartalomajánló
    -0.70
     Moslem
    -0.70
    DockStyle
    -0.68
    GraphicsUnit
    -0.67
     kasarigan
    -0.67
     تكبرها
    -0.66
     مشين
    -0.66
    POSITIVE LOGITS
    lobo
    0.42
     so
    0.42
    elsif
    0.41
    basicConfig
    0.41
     mar
    0.40
     Mar
    0.40
     TestBed
    0.39
    Datuak
    0.38
    ائد
    0.38
     it
    0.37
    Activations Density 4.879%

    No Known Activations