© 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. 15002
    Prev
    Next
    INDEX
    Explanations

    the word 'park' or 'land', in some contexts including 'health'

    oai_token-act-pair · gemini-2.0-flash

    park-related terms

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

    park

    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
    XmlAccessType
    -0.80
    principalColumn
    -0.78
    TargetException
    -0.65
    featureID
    -0.63
     continúas
    -0.60
    Portale
    -0.60
    enterOuterAlt
    -0.58
     ISNI
    -0.58
    styleType
    -0.57
    WithIOException
    -0.57
    POSITIVE LOGITS
    view
    0.50
    ie
    0.50
    net
    0.48
    View
    0.46
     Views
    0.45
     Coun
    0.45
     vulgares
    0.44
    acter
    0.44
    Views
    0.44
    io
    0.44
    Activations Density 1.683%

    No Known Activations