© 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. 25-GEMMASCOPE-TRANSCODER-16K
    7. 6066
    Prev
    Next
    INDEX
    Explanations

    food items and related descriptive words

    oai_token-act-pair · gemini-2.0-flash

    food reviews

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_25/width_16k/average_l0_41
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.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
    XmlAccessorType
    -0.60
    Ссылки
    -0.57
    Personensuche
    -0.56
    ariat
    -0.56
    LoadScene
    -0.55
    OrFail
    -0.54
    IonicModule
    -0.53
    fjspx
    -0.52
    expandindo
    -0.51
    出版年
    -0.50
    POSITIVE LOGITS
    prefixer
    0.50
    principalTable
    0.48
    GB
    0.47
     busy
    0.46
     DEL
    0.46
    zzar
    0.46
    findpost
    0.46
     Del
    0.46
    hintText
    0.45
     Bathroom
    0.44
    Activations Density 12.446%

    No Known Activations