© 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. 21-GEMMASCOPE-TRANSCODER-16K
    7. 3058
    Prev
    Next
    INDEX
    Explanations

    numbers, especially as part of location or angle coordinates

    oai_token-act-pair · gemini-2.0-flash

    variations of the word "degree"

    np_token-act-pair-logits · gpt-4o-mini

    numbers

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_21/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.21.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
     doInBackground
    -0.80
     يتيمه
    -0.76
    InitVars
    -0.74
    EndContext
    -0.73
    hyrchwyd
    -0.72
     Lightboxes
    -0.66
    PositiveButton
    -0.65
    WithIOException
    -0.64
    henswürdigkeiten
    -0.63
    StructEnd
    -0.63
    POSITIVE LOGITS
     degree
    2.27
     degrees
    2.06
    degree
    2.02
     Degree
    1.93
    Degree
    1.84
     DEGREE
    1.80
     Degrees
    1.70
    degrees
    1.64
    °
    1.63
     degrés
    1.46
    Activations Density 3.210%

    No Known Activations