© 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. 15234
    Prev
    Next
    INDEX
    Explanations

    a mix of words from reviews about products/devices and music.

    oai_token-act-pair · gemini-2.0-flash

    forms of the verb "have"

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

    have

    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
    ⓧ
    -0.68
     containing
    -0.60
    Rohy
    -0.58
     contenant
    -0.54
    ScopeManager
    -0.54
    ArrowToggle
    -0.53
    èdia
    -0.51
    BuilderFactory
    -0.50
    LElement
    -0.50
     Roskov
    -0.50
    POSITIVE LOGITS
     had
    1.14
     having
    1.08
     Have
    1.05
     have
    1.05
     has
    1.02
    Have
    1.02
    having
    1.02
     có
    0.99
    have
    0.98
     HAVING
    0.96
    Activations Density 2.973%

    No Known Activations