© 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. 3409
    Prev
    Next
    INDEX
    Explanations

    measurements involving numbers and units like "cm"

    oai_token-act-pair · gemini-2.0-flash

    measurements and dimensions

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

    Measurements and sizes

    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
     foot
    -1.77
     feet
    -1.65
    foot
    -1.52
     Foot
    -1.45
     Feet
    -1.42
     FOOT
    -1.38
     FEET
    -1.34
    Foot
    -1.34
    feet
    -1.30
    Feet
    -1.23
    POSITIVE LOGITS
     Maur
    0.66
    ㎜
    0.59
     Numerade
    0.59
     Cæsar
    0.58
    WriteBarrier
    0.56
     mills
    0.55
    ñora
    0.54
    mills
    0.54
     Mame
    0.54
     -->>
    0.54
    Activations Density 1.569%

    No Known Activations