© 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. 8040
    Prev
    Next
    INDEX
    Explanations

    terms related to computer information systems

    oai_token-act-pair · gemini-2.0-flash

    stealing data

    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
    Data
    -0.67
    Autoritní
    -0.62
    DialogContent
    -0.60
    ReusableCell
    -0.59
     Data
    -0.56
     piece
    -0.55
    piece
    -0.54
    Pieces
    -0.53
    setData
    -0.52
    data
    -0.52
    POSITIVE LOGITS
    onViewCreated
    0.63
    detectChanges
    0.61
     nakalista
    0.59
    FieldBuilder
    0.56
    Хьажоргаш
    0.55
    httphttps
    0.55
    NamedQuery
    0.52
    ⓘ
    0.52
    Salta
    0.52
     GetEnumerator
    0.51
    Activations Density 15.591%

    No Known Activations