© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 4-GEMMASCOPE-TRANSCODER-16K
    7. 11752
    Prev
    Next
    INDEX
    Explanations

    verbs related to system administration, control and design and words related to governance, power and politics.

    oai_token-act-pair · gemini-2.0-flash

    control, guide, manage

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_4/width_16k/average_l0_88
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.4.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
    sen
    -0.42
    My
    -0.41
    ix
    -0.41
    —
    -0.40
    ax
    -0.39
    This
    -0.39
    –
    -0.38
    my
    -0.36
    False
    -0.36
    <b>
    -0.36
    POSITIVE LOGITS
    MLLoader
    1.13
    WriteBarrier
    1.03
     Roskov
    0.99
    RegistryLite
    0.99
     CreateTagHelper
    0.96
    KURZBESCHREIBUNG
    0.94
    rungsseite
    0.93
     виправивши
    0.93
    出版年
    0.91
     resourceCulture
    0.90
    Activations Density 16.237%

    No Known Activations