© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 21-GEMMASCOPE-TRANSCODER-16K
    7. 10228
    Prev
    Next
    INDEX
    Explanations

    the word 'low' and terms it is associated with, such as 'low-cost', and `low income`

    oai_token-act-pair · gemini-2.0-flash

    the word 'low' in various contexts

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

    low

    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
     Penh
    -0.53
    IsContent
    -0.52
    NOPQRST
    -0.50
     <=",
    -0.49
    ServletException
    -0.48
    fully
    -0.48
     ense
    -0.47
     vouch
    -0.47
    umma
    -0.46
     emprunt
    -0.44
    POSITIVE LOGITS
    ंदीखरीदारी
    0.73
     مرئيه
    0.67
    providedIn
    0.65
    InstanceState
    0.57
     resourceCulture
    0.56
     jScrollPane
    0.56
    SaveChangesAsync
    0.56
    日閲覧
    0.55
     karbon
    0.55
    GraphicsUnit
    0.55
    Activations Density 0.881%

    No Known Activations