© 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. 7177
    Prev
    Next
    INDEX
    Explanations

    nouns related to transportation and boats

    oai_token-act-pair · gemini-2.0-flash

    words related to trucks and transport

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

    vehicles

    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
     समीक्षाओं
    -0.49
    évaluateur
    -0.46
    Coordonnées
    -0.44
    SerializedSize
    -0.44
     ribu
    -0.43
    kuuta
    -0.42
    sweetalert
    -0.41
    RegressionTest
    -0.39
    acyjny
    -0.38
     itemView
    -0.38
    POSITIVE LOGITS
     esternos
    0.70
    :].
    0.69
    AddTagHelper
    0.65
    contentLoaded
    0.61
     initComponents
    0.60
     parked
    0.60
    erdings
    0.59
    mpotent
    0.58
    Спасылкі
    0.57
    DockStyle
    0.57
    Activations Density 5.735%

    No Known Activations