© 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. 22-GEMMASCOPE-TRANSCODER-16K
    7. 13087
    Prev
    Next
    INDEX
    Explanations

    sentences that contain conjunctions

    oai_token-act-pair · gemini-2.0-flash

    But

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_22/width_16k/average_l0_15
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.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
     Whether
    -0.53
    Whether
    -0.48
    l
    -0.43
    G
    -0.41
    4
    -0.41
    b
    -0.40
    So
    -0.40
    L
    -0.39
    ↵↵
    -0.39
    -
    -0.39
    POSITIVE LOGITS
    tagHelperRunner
    1.13
     HasFactory
    1.12
     myſelf
    1.08
    LabelTagHelper
    1.05
     Normdatei
    1.04
    AutoScaleMode
    1.03
     विश्वसनीयता
    1.02
    RenderAtEndOf
    1.00
     незавершена
    0.99
     protoimpl
    0.99
    Activations Density 4.550%

    No Known Activations