© 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. 7849
    Prev
    Next
    INDEX
    Explanations

    various words related to modality, purpose, and possibility

    oai_token-act-pair · gemini-2.0-flash

    analysis and interpretation

    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
     betweenstory
    -0.69
     Савезне
    -0.60
     للمعارف
    -0.60
    yntaxException
    -0.58
    AKERS
    -0.57
    SOUNDBITE
    -0.57
    esez
    -0.55
     utafitiHapana
    -0.54
    ufact
    -0.54
     transférez
    -0.53
    POSITIVE LOGITS
     réduit
    0.56
     riduzione
    0.54
     FetchType
    0.54
     réduire
    0.50
     nltk
    0.49
     rédu
    0.49
     reduced
    0.48
    Reduction
    0.48
    reduced
    0.47
    Décès
    0.47
    Activations Density 7.895%

    No Known Activations