© 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. 24-GEMMASCOPE-TRANSCODER-16K
    7. 7755
    Prev
    Next
    INDEX
    Explanations

    the stem "ira" in words like "desirable" or "undesirable"

    oai_token-act-pair · gemini-2.0-flash

    chemical processes

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_24/width_16k/average_l0_37
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.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
     SB
    -1.27
     MB
    -1.27
     EB
    -1.26
     RB
    -1.24
     WB
    -1.23
     UB
    -1.22
     CB
    -1.20
     HB
    -1.19
     PB
    -1.19
     OB
    -1.19
    POSITIVE LOGITS
    DockStyle
    0.91
    SourceChecksum
    0.66
     وتسجيلات
    0.64
     AssemblyCulture
    0.63
     AttributeSet
    0.60
    FormTagHelper
    0.59
     propOrder
    0.57
    oa̍t
    0.55
    rungsseite
    0.54
    titleMargin
    0.54
    Activations Density 1.558%

    No Known Activations