© 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. 18-GEMMASCOPE-TRANSCODER-16K
    7. 6730
    Prev
    Next
    INDEX
    Explanations

    words and phrases related to the dark side, secrets, the past, and the unknown.

    oai_token-act-pair · gemini-2.0-flash

    secrets and the past

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_18/width_16k/average_l0_13
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.18.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
    writerow
    -0.73
    ⓧ
    -0.67
    MessageTagHelper
    -0.66
    WireFormatLite
    -0.65
    dafx
    -0.61
    ValueStyle
    -0.61
    ponses
    -0.59
    ########.
    -0.57
    :+:
    -0.57
     MonoBehaviour
    -0.57
    POSITIVE LOGITS
     past
    1.82
     Past
    1.44
    past
    1.38
    Past
    1.38
     PAST
    1.32
     Vergangenheit
    1.24
     passato
    1.14
    PAST
    1.13
     pasado
    1.10
     прошлого
    1.06
    Activations Density 0.638%

    No Known Activations