© 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. 22-GEMMASCOPE-TRANSCODER-16K
    7. 10592
    Prev
    Next
    INDEX
    Explanations

    titles of works of art, such as movies or shows

    oai_token-act-pair · gemini-2.0-flash

    movie reviews

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_22/width_16k/average_l0_15
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.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
    &
    -0.49
     &
    -0.47
     e
    -0.45
     false
    -0.41
     or
    -0.40
     ou
    -0.40
     AND
    -0.40
     .
    -0.39
    рованной
    -0.39
    \
    -0.39
    POSITIVE LOGITS
     InputDecoration
    0.86
    />";
    0.82
    tvguidetime
    0.82
    RuleContext
    0.82
     ProtoMessage
    0.81
    __(/*!
    0.78
    Autoritní
    0.77
    \{\\
    0.76
    RegistryLite
    0.75
    encodeWith
    0.75
    Activations Density 0.330%

    No Known Activations