© 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. 18-GEMMASCOPE-TRANSCODER-16K
    7. 5560
    Prev
    Next
    INDEX
    Explanations

    intensifiers used to describe a problem or mistake.

    oai_token-act-pair · gemini-2.0-flash

    scale and magnitude

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_18/width_16k/average_l0_13
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.18.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
    SuspendLayout
    -0.61
    RRect
    -0.52
    Autoritní
    -0.50
     toekomst
    -0.49
     StringTokenizer
    -0.48
     invariant
    -0.47
    ugier
    -0.46
    fieldLabel
    -0.45
     Identität
    -0.44
     taban
    -0.43
    POSITIVE LOGITS
     scale
    1.55
     magnitude
    1.41
     scope
    1.35
     Scale
    1.30
     extent
    1.25
     SCALE
    1.22
    scale
    1.17
     magnitud
    1.13
     scales
    1.10
     Magnitude
    1.10
    Activations Density 1.025%

    No Known Activations