© 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
    2. Gemma-2-2B
    3. 21-GEMMASCOPE-TRANSCODER-16K
    4. 6198
    Prev
    Next
    INDEX
    Explanations

    transitions between sentences or phrases including punctuation, conjunctions, and some HTML tags.

    oai_token-act-pair · gemini-2.0-flash

    variations of the word "here"

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

    here

    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
     мәкал
    -0.71
     GenerationType
    -0.60
    featureID
    -0.60
     disambiguazione
    -0.57
     kaynağından
    -0.55
    Westfalen
    -0.54
    enumii
    -0.54
    StoreMessageInfo
    -0.53
    OOTDTY
    -0.52
    dients
    -0.52
    POSITIVE LOGITS
     here
    4.03
    here
    3.19
     Here
    3.11
    Here
    3.00
     aquí
    2.95
     ici
    2.75
     здесь
    2.67
     HERE
    2.66
     aqui
    2.66
     aici
    2.63
    Activations Density 3.767%

    No Known Activations