© 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. 8-GEMMASCOPE-TRANSCODER-16K
    7. 1366
    Prev
    Next
    INDEX
    Explanations

    speech or text that comes from an interview

    oai_token-act-pair · gemini-2.0-flash

    interview

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_8/width_16k/average_l0_52
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.8.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
     
    -0.55
     x
    -0.55
    x
    -0.53
    '
    -0.52
     i
    -0.51
     S
    -0.50
     "
    -0.50
     '
    -0.48
     of
    -0.48
     D
    -0.48
    POSITIVE LOGITS
     Efq
    1.16
     myſelf
    1.16
     houſe
    1.13
     ſche
    1.13
     itſelf
    1.12
     whoſe
    1.11
     pleaſure
    1.10
     Eſ
    1.09
     Anſ
    1.09
     Reſ
    1.08
    Activations Density 0.481%

    No Known Activations