© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 21-GEMMASCOPE-TRANSCODER-16K
    7. 14595
    Prev
    Next
    INDEX
    Explanations

    words and phrases that describe potential or observed effects and changes

    oai_token-act-pair · gemini-2.0-flash

    forms of the verb 'have'

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

    having

    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
     effect
    -0.57
    effect
    -0.55
    utup
    -0.54
    luit
    -0.53
     Behold
    -0.52
     Effect
    -0.50
     contienen
    -0.50
     gevolg
    -0.49
     EFFECT
    -0.48
     følger
    -0.47
    POSITIVE LOGITS
     having
    1.70
    having
    1.63
     HAVING
    1.49
     Having
    1.48
    Having
    1.47
     had
    1.41
     Have
    1.27
    Have
    1.24
    have
    1.22
     have
    1.21
    Activations Density 2.629%

    No Known Activations