© 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. 6-GEMMASCOPE-TRANSCODER-16K
    7. 15585
    Prev
    Next
    INDEX
    Explanations

    subjective opinions and conversational filler

    oai_token-act-pair · gemini-2.0-flash

    kind

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_6/width_16k/average_l0_95
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.6.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
     kind
    -1.52
    kind
    -1.27
    Kind
    -1.21
     Kind
    -1.20
     sort
    -1.20
     KIND
    -1.18
    KIND
    -1.06
    sort
    -1.02
     kinds
    -0.97
     kinda
    -0.90
    POSITIVE LOGITS
    Autoritní
    0.71
    OGND
    0.70
    TagHelper
    0.68
    LEncoder
    0.66
    AnchorStyles
    0.66
     Baillargeon
    0.63
    ußer
    0.62
     désolés
    0.62
    <bos>
    0.61
    Controllo
    0.60
    Activations Density 20.217%

    No Known Activations