© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-2B
    3. 21-GEMMASCOPE-TRANSCODER-16K
    4. 5716
    Prev
    Next
    INDEX
    Explanations

    small, common connecting words like "of", "to", and prepositions, as well as words relating to parts or stages.

    oai_token-act-pair · gemini-2.0-flash

    programming-related terminology or code structures

    np_token-act-pair-logits · gpt-4o-mini

    Internet-related

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_21/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.21.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
     t
    -0.41
     to
    -0.40
     daher
    -0.36
    res
    -0.36
     recherchez
    -0.33
    its
    -0.32
    ling
    -0.32
     Corporation
    -0.32
    dis
    -0.31
    ret
    -0.31
    POSITIVE LOGITS
    SharedCtor
    1.16
     disambiguazione
    1.05
    ⓧ
    1.02
    RegistryLite
    1.02
     &___
    1.00
    dafx
    0.94
    DockStyle
    0.93
    AnchorStyles
    0.93
     InputDecoration
    0.92
    RegressionTest
    0.92
    Activations Density 2.794%

    No Known Activations