© 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
    2. Gemma-2-2B
    3. 25-GEMMASCOPE-TRANSCODER-16K
    4. 8962
    Prev
    Next
    INDEX
    Explanations

    words related to expressing personal sentiments and opinions, especially in a formal or professional context.

    oai_token-act-pair · gemini-2.0-flash

    foreign words

    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
     Efficient
    -1.20
     Effective
    -1.19
     effective
    -1.19
    Efficient
    -1.17
     efficient
    -1.16
    Effective
    -1.16
    effective
    -1.07
     EFFECTIVE
    -1.05
     proper
    -1.05
     Proper
    -1.00
    POSITIVE LOGITS
     Theſe
    0.63
     Boucher
    0.52
     оригіналу
    0.49
     tache
    0.49
     Airports
    0.48
    之色
    0.48
     Aniston
    0.47
     pleaſure
    0.47
     Wikimédia
    0.47
    haustible
    0.46
    Activations Density 20.147%

    No Known Activations