© 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. 5690
    Prev
    Next
    INDEX
    Explanations

    the word "in" followed or preceded by a short sequence of characters or another short word.

    oai_token-act-pair · gemini-2.0-flash

    terms related to data storage and resource management

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

    in

    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
    gnition
    -0.94
    pecially
    -0.88
    ratulations
    -0.83
    polation
    -0.80
    resents
    -0.73
    ENZO
    -0.72
    ficulty
    -0.72
    uedes
    -0.72
    cillor
    -0.72
    orgeous
    -0.71
    POSITIVE LOGITS
    StoreMessageInfo
    0.82
     resourceCulture
    0.80
     صوتيه
    0.79
    us
    0.70
    Datuak
    0.67
     للاسماء
    0.61
     quæ
    0.60
    es
    0.60
    em
    0.59
    InjectAttribute
    0.59
    Activations Density 5.896%

    No Known Activations