© 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. 11758
    Prev
    Next
    INDEX
    Explanations

    words related to settings, actions and objects within a narrative or story.

    oai_token-act-pair · gemini-2.0-flash

    lodging, travel

    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
    <bos>
    -1.85
     autorytatywna
    -1.34
     ostavi
    -1.15
    Portail
    -1.15
     resourceCulture
    -1.04
    Autoritní
    -1.03
    adaptiveStyles
    -0.96
     '\\;'
    -0.96
    InjectAttribute
    -0.95
    __":
    -0.95
    POSITIVE LOGITS
    .
    0.49
    [toxicity=0]
    0.47
    X
    0.46
     jdbcTemplate
    0.44
     nõ
    0.44
    1
    0.43
    providedIn
    0.41
    Is
    0.41
    qiu
    0.41
    Z
    0.41
    Activations Density 2.728%

    No Known Activations