© 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. 25-GEMMASCOPE-TRANSCODER-16K
    7. 8289
    Prev
    Next
    INDEX
    Explanations

    words related to sales and technical solutions, especially "solution" and "offer".

    oai_token-act-pair · gemini-2.0-flash

    Not English

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_25/width_16k/average_l0_41
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.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
     solution
    -2.98
     Solution
    -2.75
    solution
    -2.66
    Solution
    -2.61
     solutions
    -2.53
     SOLUTION
    -2.39
    Solutions
    -2.34
     Solutions
    -2.30
    solutions
    -2.25
     Lösung
    -2.20
    POSITIVE LOGITS
    новништво
    0.70
    KommentareTeilen
    0.69
     ویکی‌پدیا
    0.55
    期刊论文
    0.53
     rappelle
    0.50
     دیکھیے
    0.49
    Демографія
    0.48
     op
    0.47
    qtype
    0.47
    op
    0.45
    Activations Density 4.096%

    No Known Activations