© 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. 24-GEMMASCOPE-TRANSCODER-16K
    4. 3398
    Prev
    Next
    INDEX
    Explanations

    a mix of common English words and phrases, along with some possible loan words or proper nouns, with no clear consistent theme

    oai_token-act-pair · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_24/width_16k/average_l0_37
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.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
     MessageBoxIcon
    -0.61
     виправивши
    -0.59
     Extragalactic
    -0.58
     Alegre
    -0.57
    例句
    -0.55
    GEBURTS
    -0.55
    AutoScaleMode
    -0.55
    cokinetic
    -0.54
    noons
    -0.54
    ConverterFactory
    -0.54
    POSITIVE LOGITS
     loài
    0.45
    TypedDataSet
    0.44
    gouv
    0.41
    rippa
    0.41
    џ
    0.40
    सन्दर्भ
    0.39
     otomatig
    0.39
     sex
    0.39
    jstor
    0.38
    Gra
    0.38
    Activations Density 0.180%

    No Known Activations