© 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. 14821
    Prev
    Next
    INDEX
    Explanations

    instances of the word "Visual" or related terms that deal with sight

    oai_token-act-pair · gemini-2.0-flash

    terms related to "Visual"

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

    visual

    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
     becauſe
    -0.75
     itſelf
    -0.72
     ſche
    -0.71
     Theſe
    -0.71
     Anſ
    -0.70
    IContainer
    -0.70
     myſelf
    -0.70
     himſelf
    -0.70
     uſed
    -0.69
    expandindo
    -0.69
    POSITIVE LOGITS
    zzar
    0.51
     szóci
    0.44
     half
    0.44
    дцать
    0.43
     most
    0.41
    yelitis
    0.41
    emption
    0.41
    EndProject
    0.41
    MutableLiveData
    0.41
     ray
    0.41
    Activations Density 1.837%

    No Known Activations