© 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
    2. Gemma-2-2B
    3. 0-GEMMASCOPE-TRANSCODER-16K
    4. 6710
    Prev
    Next
    INDEX
    Explanations

    xml or html tags and the word "expected"

    oai_token-act-pair · gemini-2.0-flash

    "<" symbol

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_0/width_16k/average_l0_76
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.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
    <
    -1.26
    \
    -1.16
     
    -1.11
    <strong>
    -1.06
     the
    -1.03
    >
    -0.97
    2
    -0.94
    1
    -0.91
    ↵↵
    -0.90
    ↵
    -0.90
    POSITIVE LOGITS
    ^(@)
    1.93
     itſelf
    1.80
    ſelf
    1.70
     doubtnut
    1.70
     Efq
    1.70
     raiſ
    1.64
     Jefus
    1.63
     myſelf
    1.63
    ſelves
    1.60
     Majefty
    1.60
    Activations Density 0.883%

    No Known Activations