© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 0-GEMMASCOPE-TRANSCODER-16K
    7. 15868
    Prev
    Next
    INDEX
    Explanations

    disclaimers found in software licenses

    oai_token-act-pair · gemini-2.0-flash

    liable

    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
    •the_software_is_provided_"as:8f2232d9-1f50-5497-9669-5fe230633d9c:gemma-2-2b:gemmascope-transcoder-16k
    Top frequency features for prompt

    No Comments

    Negative Logits
    <bos>
    -2.08
    ſelf
    -0.69
    ſelves
    -0.66
    utilisons
    -0.65
     ſche
    -0.65
    🏾
    -0.62
    Personensuche
    -0.62
     simplifié
    -0.61
     itſelf
    -0.59
    rungsseite
    -0.58
    POSITIVE LOGITS
    WEBPACK
    0.66
     Normdatei
    0.60
    TestingModule
    0.57
    AnchorStyles
    0.57
    出版年
    0.56
     onOptions
    0.56
    SequentialGroup
    0.53
    god
    0.50
     /\.(
    0.50
    levi
    0.49
    Activations Density 2.481%

    No Known Activations