© 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. 22-GEMMASCOPE-TRANSCODER-16K
    7. 3532
    Prev
    Next
    INDEX
    Explanations

    the token "Wood"

    oai_token-act-pair · gemini-2.0-flash

    Wood

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_22/width_16k/average_l0_15
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.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
    StoryboardSegue
    -0.51
     honte
    -0.49
    ussen
    -0.46
     gloire
    -0.46
     fören
    -0.46
     CHtml
    -0.46
    gomery
    -0.45
     quæ
    -0.45
    نع
    -0.45
    ayuno
    -0.45
    POSITIVE LOGITS
    awtextra
    0.79
    GEBURTSDATUM
    0.75
    expandindo
    0.67
    NameInMap
    0.63
    EDEFAULT
    0.60
    Portály
    0.60
    ChildScrollView
    0.58
     invokingState
    0.56
    يكب
    0.56
    migrationBuilder
    0.56
    Activations Density 0.718%

    No Known Activations