© 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. 22-GEMMASCOPE-TRANSCODER-16K
    7. 10135
    Prev
    Next
    INDEX
    Explanations

    non-English place names or scientific terms with special characters

    oai_token-act-pair · gemini-2.0-flash

    Scientific text/compounds

    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
    تقاوى
    -0.96
    SharedCtor
    -0.77
    IntoConstraints
    -0.72
     виправивши
    -0.70
    ISupport
    -0.70
     otomatig
    -0.70
    AutoScaleMode
    -0.67
    @[+][
    -0.65
    المناصب
    -0.65
    AndEndTag
    -0.64
    POSITIVE LOGITS
    tagens
    0.48
     Mung
    0.45
    <bos>
    0.44
    scryfall
    0.42
    tiy
    0.41
    liani
    0.41
     tudom
    0.40
    paramString
    0.40
    localVar
    0.39
    sproz
    0.38
    Activations Density 0.390%

    No Known Activations