© 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
    3. Gemma-2-2B
    5. 21-GEMMASCOPE-TRANSCODER-16K
    7. 11327
    Prev
    Next
    INDEX
    Explanations

    the suffix "es", "st" or "ly".

    oai_token-act-pair · gemini-2.0-flash

    words related to test subjects or assessments

    np_token-act-pair-logits · gpt-4o-mini
    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
    EndInit
    -0.96
    EDEFAULT
    -0.88
     unknownFields
    -0.88
    IUrlHelper
    -0.86
    ISupport
    -0.86
    ti
    -0.84
    DockStyle
    -0.78
    +:+
    -0.77
    InvalidProtocol
    -0.75
    webElementXpaths
    -0.75
    POSITIVE LOGITS
    site
    0.40
    面
    0.35
     sile
    0.35
    ewa
    0.35
    ed
    0.34
    ep
    0.33
    EDI
    0.33
     full
    0.32
    top
    0.32
    ients
    0.32
    Activations Density 1.243%

    No Known Activations