© 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. 0-GEMMASCOPE-TRANSCODER-16K
    7. 7827
    Prev
    Next
    INDEX
    Explanations

    words relating to opinions, reviews, and discussing with someone

    oai_token-act-pair · gemini-2.0-flash

    interview/feedback

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_0/width_16k/average_l0_76
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.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
    “
    -0.63
     le
    -0.59
     la
    -0.57
    ge
    -0.56
    （
    -0.54
    ’
    -0.54
    ”
    -0.53
    anga
    -0.53
    ://
    -0.52
     value
    -0.52
    POSITIVE LOGITS
     InputDecoration
    1.22
     سكانية
    1.11
     يتيمه
    1.09
     EconPapers
    0.97
    ніципалі
    0.96
    AddTagHelper
    0.93
     demurrer
    0.90
     tartalomajánló
    0.88
     quarries
    0.85
     gawas
    0.85
    Activations Density 1.123%

    No Known Activations