© 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. 6184
    Prev
    Next
    INDEX
    Explanations

    text about departments within a college or university and the degrees they offer

    oai_token-act-pair · gemini-2.0-flash

    academic program-related terms

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

    academic degree programs

    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
    AndEndTag
    -0.81
     समीक्षाएं
    -0.72
    rungsseite
    -0.71
     myſelf
    -0.71
    ContentAsync
    -0.70
    исленность
    -0.68
     initComponents
    -0.67
    webElementXpaths
    -0.66
    LookAnd
    -0.63
     leaſt
    -0.63
    POSITIVE LOGITS
     degree
    0.47
     concentration
    0.47
     program
    0.46
     concentrations
    0.46
     ActivatedRoute
    0.44
    ym
    0.43
     Was
    0.42
    ModelAttribute
    0.42
     Program
    0.42
    getMinutes
    0.42
    Activations Density 2.921%

    No Known Activations