© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 21-GEMMASCOPE-TRANSCODER-16K
    7. 11485
    Prev
    Next
    INDEX
    Explanations

    instances of the verb "to be" in various tenses

    oai_token-act-pair · gemini-2.0-flash

    words related to evidence presentation

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

    been

    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
    djangoproject
    -0.55
    CodeAttribute
    -0.52
     tecnici
    -0.48
     forfait
    -0.46
    pintura
    -0.46
    GOTREF
    -0.46
    Litteratur
    -0.45
    secutive
    -0.45
    imedes
    -0.43
    addError
    -0.43
    POSITIVE LOGITS
     shown
    2.50
     show
    2.44
    show
    2.16
     Show
    2.13
    Show
    2.06
     showed
    2.06
    shown
    2.06
     shows
    2.05
     showing
    2.03
     Shown
    2.00
    Activations Density 6.323%

    No Known Activations