© 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. 4708
    Prev
    Next
    INDEX
    Explanations

    words that are the past tense of verbs and words relating to administration.

    oai_token-act-pair · gemini-2.0-flash

    with

    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
     aim
    -0.42
    PropertyChanging
    -0.41
    StructEnd
    -0.39
    Жен
    -0.39
    DrawerToggle
    -0.39
    зап
    -0.38
     L
    -0.37
    PROTOBUF
    -0.37
     Unit
    -0.37
    uti
    -0.36
    POSITIVE LOGITS
     with
    1.56
    with
    1.25
     WITH
    1.23
     avec
    1.18
     With
    1.18
    With
    1.12
     dengan
    1.10
    WITH
    1.03
     với
    1.02
    avec
    1.01
    Activations Density 1.183%

    No Known Activations