© 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. 6211
    Prev
    Next
    INDEX
    Explanations

    the phrase "Link to post"

    oai_token-act-pair · gemini-2.0-flash

    links to posts

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

    link

    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
    roek
    -0.88
     BorderSide
    -0.81
    Xna
    -0.80
     defaultstate
    -0.79
    KommentareTeilen
    -0.79
     snippetHide
    -0.77
    posedge
    -0.73
     betweenstory
    -0.72
    OrBuilder
    -0.71
    ieteur
    -0.70
    POSITIVE LOGITS
    >`;
    0.45
     way
    0.44
     st
    0.44
     to
    0.43
     Day
    0.42
     between
    0.42
    ty
    0.42
    mas
    0.41
    ma
    0.41
    Dy
    0.40
    Activations Density 1.646%

    No Known Activations