© 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. 6195
    Prev
    Next
    INDEX
    Explanations

    sentences that are product reviews that are somewhat positive, containing "is" and other value judgements

    oai_token-act-pair · gemini-2.0-flash

    keywords related to defining characteristics or attributes

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

    code, summaries or reviews

    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
    تقاوى
    -0.60
    WriteTagHelper
    -0.55
    Tis
    -0.46
     Meilleur
    -0.46
    EndContext
    -0.46
    InSection
    -0.46
    Pag
    -0.45
     ral
    -0.45
     الرياضيه
    -0.44
    global
    -0.44
    POSITIVE LOGITS
    Zitat
    0.60
    uxxxx
    0.57
    DEFIN
    0.56
    rrggbb
    0.56
    ReusableCell
    0.54
     réputation
    0.53
    คง
    0.52
    ioutil
    0.52
     defini
    0.51
     mía
    0.50
    Activations Density 0.654%

    No Known Activations