© 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. 6345
    Prev
    Next
    INDEX
    Explanations

    months and days of the month

    oai_token-act-pair · gemini-2.0-flash

    tokens related to dates or October events

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

    October and September

    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
    ICTS
    -0.44
     manqué
    -0.42
    sejarah
    -0.42
     leçons
    -0.42
     doré
    -0.41
    EnumValue
    -0.41
    grafia
    -0.40
    нциклопедия
    -0.40
     ervan
    -0.40
    aser
    -0.39
    POSITIVE LOGITS
     GenerationType
    0.90
    enumi
    0.84
    __*/
    0.76
    出版年
    0.75
    Rujuakan
    0.70
    HomeAsUpEnabled
    0.68
    fjspx
    0.68
    IMPORTED
    0.68
    StoreMessageInfo
    0.66
    PerformLayout
    0.66
    Activations Density 0.731%

    No Known Activations