© 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. 3-GEMMASCOPE-TRANSCODER-16K
    7. 8977
    Prev
    Next
    INDEX
    Explanations

    the phrase "ontarget-", and sometimes words ending in "gene" or indicating a change of state, particularly "again" and "up"

    oai_token-act-pair · gemini-2.0-flash

    scientific research

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_3/width_16k/average_l0_54
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.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
     Jefus
    -1.02
     Majefty
    -1.02
     Efq
    -1.02
     myſelf
    -1.00
     whoſe
    -0.93
     Monfieur
    -0.92
     itſelf
    -0.91
     raiſ
    -0.91
     becauſe
    -0.88
     himſelf
    -0.86
    POSITIVE LOGITS
    <bos>
    0.54
     
    0.52
     off
    0.50
    -
    0.49
     J
    0.47
     ter
    0.46
    je
    0.46
     The
    0.46
    </em>
    0.46
     ‘
    0.45
    Activations Density 1.073%

    No Known Activations