© 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. 11428
    Prev
    Next
    INDEX
    Explanations

    references to time of day, especially work hours

    oai_token-act-pair · gemini-2.0-flash

    terms related to business operations or hours

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

    hours

    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
    دانشنامهٔ
    -0.64
    RepeatedField
    -0.58
    ⓘ
    -0.56
    #+#
    -0.55
     tartalomajánló
    -0.54
    RetentionPolicy
    -0.54
    AndEndTag
    -0.54
     SUDOC
    -0.54
     NUKAT
    -0.54
    ISupport
    -0.51
    POSITIVE LOGITS
     hours
    1.05
     opening
    1.03
     working
    1.00
     business
    0.83
    Opening
    0.82
     Opening
    0.82
    opening
    0.82
     normal
    0.81
     Hours
    0.81
     operating
    0.79
    Activations Density 1.383%

    No Known Activations