© 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. 6318
    Prev
    Next
    INDEX
    Explanations

    numbers relating to temperature and water, along with possessive pronouns

    oai_token-act-pair · gemini-2.0-flash

    specialized vocabulary related to scientific or technical contexts

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

    Celsius temperatures

    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
     Degree
    -0.54
     froide
    -0.54
     degrés
    -0.53
     pulumi
    -0.53
    denk
    -0.51
     Temp
    -0.49
     velkommen
    -0.49
     Warming
    -0.49
     GoogleFonts
    -0.49
     Temperature
    -0.49
    POSITIVE LOGITS
     متعلقه
    0.96
    出版年
    0.73
    Portail
    0.71
    GraphicsUnit
    0.70
    TagHelper
    0.64
    InjectAttribute
    0.62
    KURZBESCHREIBUNG
    0.62
     مرئيه
    0.59
    AuthContext
    0.59
    Datuak
    0.59
    Activations Density 0.864%

    No Known Activations