© 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. 8391
    Prev
    Next
    INDEX
    Explanations

    phone numbers or otherwise structured numerical codes including digits

    oai_token-act-pair · gemini-2.0-flash

    say "5"

    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
    IsMutable
    -1.02
    tagHelperRunner
    -1.02
    ⁶
    -1.00
    .³
    -0.99
     незавершена
    -0.98
    存于互联网档案馆
    -0.96
    GEBURTSDATUM
    -0.93
     Sixteenth
    -0.93
     sixteenth
    -0.91
     sixteen
    -0.91
    POSITIVE LOGITS
     
    0.48
    5
    0.47
    guli
    0.46
     gerek
    0.44
    一見
    0.43
     gelap
    0.42
    }_
    0.42
     órganos
    0.42
    straat
    0.41
    isburg
    0.41
    Activations Density 0.518%

    No Known Activations