© 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. 4077
    Prev
    Next
    INDEX
    Explanations

    names of individuals, especially famous people and those in the film and music industries, along with associated roles or titles.

    oai_token-act-pair · gemini-2.0-flash

    past tense verbs indicating actions

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

    Biographies

    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
    ValueStyle
    -0.69
    پیوند
    -0.62
     themſelves
    -0.59
    ustimmung
    -0.57
     onBind
    -0.54
    通販
    -0.54
     חיצוניים
    -0.54
    Composable
    -0.53
    例句
    -0.52
     esterni
    -0.52
    POSITIVE LOGITS
     appeared
    0.66
    ParallelGroup
    0.59
     gained
    0.56
     rose
    0.55
     co
    0.54
     starred
    0.54
     left
    0.52
     scored
    0.49
     attracted
    0.48
     went
    0.48
    Activations Density 1.457%

    No Known Activations