© 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. 11381
    Prev
    Next
    INDEX
    Explanations

    verbs related to movement

    oai_token-act-pair · gemini-2.0-flash

    words related to escape and fleeing

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

    leaving

    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
    zepam
    -0.46
     of
    -0.45
     Rptr
    -0.45
    globin
    -0.43
    nili
    -0.43
    dw
    -0.40
     farbe
    -0.40
    ew
    -0.40
    acci
    -0.40
    one
    -0.39
    POSITIVE LOGITS
    MemoryWarning
    0.74
     the
    0.74
    Bibliograf
    0.72
    setVerticalGroup
    0.72
    Билгалдахарш
    0.70
    IUrlHelper
    0.68
    OGND
    0.67
    enterOuterAlt
    0.66
    Identyfik
    0.66
    TagMode
    0.64
    Activations Density 6.499%

    No Known Activations