© 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. 12-GEMMASCOPE-TRANSCODER-16K
    7. 14050
    Prev
    Next
    INDEX
    Explanations

    past tense verbs or the auxiliary verb "had"

    oai_token-act-pair · gemini-2.0-flash

    had

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_12/width_16k/average_l0_6
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.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
    rawtypes
    -0.40
    txtName
    -0.38
    <eos>
    -0.38
    vaiz
    -0.38
    permum
    -0.37
     moderni
    -0.35
     Nar
    -0.35
     Modern
    -0.35
     locura
    -0.34
     Grand
    -0.34
    POSITIVE LOGITS
     Efq
    0.81
     }}$}
    0.81
    DockStyle
    0.77
     ſtate
    0.77
     ―――――
    0.77
     purpoſe
    0.77
     getLayout
    0.77
    ^(@)
    0.76
    TagMode
    0.76
     ――――――――
    0.75
    Activations Density 1.476%

    No Known Activations