© 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. 0-GEMMASCOPE-TRANSCODER-16K
    7. 7664
    Prev
    Next
    INDEX
    Explanations

    the word "freedom"

    oai_token-act-pair · gemini-2.0-flash

    freedom

    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
    [
    -0.99
    (
    -0.71
    SourceChecksum
    -0.63
    /
    -0.60
    ̣ng
    -0.58
    \
    -0.56
    databind
    -0.53
    =
    -0.52
    BindingResult
    -0.52
    $=\
    -0.52
    POSITIVE LOGITS
    <bos>
    1.15
     myſelf
    1.00
     Monfieur
    0.96
     Majefty
    0.95
     raiſ
    0.94
     Efq
    0.94
     itſelf
    0.93
     Theſe
    0.93
     avoient
    0.90
    ſelves
    0.89
    Activations Density 1.435%

    No Known Activations