© 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. 22-GEMMASCOPE-TRANSCODER-16K
    7. 11705
    Prev
    Next
    INDEX
    Explanations

    words that make up sentences

    oai_token-act-pair · gemini-2.0-flash

    random short text snippets

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_22/width_16k/average_l0_15
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.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
     Normdatei
    -0.74
    ValueStyle
    -0.68
     estimés
    -0.65
    antaranya
    -0.64
    /**
    -0.62
    ConstraintMaker
    -0.60
    spesies
    -0.60
    MemoryWarning
    -0.60
     tartalomajánló
    -0.60
     GoogleFonts
    -0.59
    POSITIVE LOGITS
    thâu
    0.55
     Spezial
    0.48
    erschutz
    0.48
    ENCH
    0.47
     trou
    0.47
    Contours
    0.46
    יצוב
    0.46
     continúas
    0.46
    mauri
    0.45
     svar
    0.44
    Activations Density 5.962%

    No Known Activations