© 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. 19-GEMMASCOPE-TRANSCODER-16K
    7. 2344
    Prev
    Next
    INDEX
    Explanations

    instances of the word "ha," or forms of the verb "be"

    oai_token-act-pair · gemini-2.0-flash

    Ha

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_19/width_16k/average_l0_12
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.19.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
     EconPapers
    -0.51
     AssemblyTitle
    -0.50
    aarrggbb
    -0.47
    "{\
    -0.47
     Meli
    -0.47
    sehen
    -0.46
    contentLoaded
    -0.45
     standardi
    -0.45
    ("/{
    -0.44
     hepat
    -0.44
    POSITIVE LOGITS
    Personensuche
    1.02
    CloseOperation
    0.75
    RenderAtEndOf
    0.66
    pushFollow
    0.63
    Portale
    0.57
    AndroidJUnit
    0.56
     jScrollPane
    0.55
    ReusableCell
    0.54
     SwitchCompat
    0.53
     ifrån
    0.53
    Activations Density 0.415%

    No Known Activations