© 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. 24-GEMMASCOPE-TRANSCODER-16K
    7. 8381
    Prev
    Next
    INDEX
    Explanations

    words and phrases related to multiple items or layers

    oai_token-act-pair · gemini-2.0-flash

    multi

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_24/width_16k/average_l0_37
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.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
     Multi
    -3.16
    Multi
    -3.09
     multi
    -3.09
    multi
    -2.98
     MULT
    -2.63
     MULTI
    -2.58
    MULTI
    -2.48
    MULT
    -2.34
     Multiple
    -2.27
    Multiple
    -2.17
    POSITIVE LOGITS
    BufferException
    0.55
     termica
    0.53
    eleste
    0.52
    InjectMocks
    0.50
     myſelf
    0.50
     Generale
    0.50
     Autorizaciones
    0.49
    ashian
    0.49
    ArgsConstructor
    0.48
    <caption>
    0.48
    Activations Density 3.456%

    No Known Activations