© 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. 836
    Prev
    Next
    INDEX
    Explanations

    action verbs in various tenses and forms

    oai_token-act-pair · gemini-2.0-flash

    reflexive pronouns

    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
    InputBorder
    -0.40
    HasColumnType
    -0.39
    aryan
    -0.39
    xmlWriter
    -0.39
    PLIES
    -0.38
     numerus
    -0.37
    zionare
    -0.37
    wesen
    -0.37
    hhhhhhhh
    -0.36
    ništvo
    -0.36
    POSITIVE LOGITS
     themselves
    3.39
     himself
    3.34
     herself
    3.27
    themselves
    3.13
     itself
    3.13
     ourselves
    3.11
     yourself
    3.02
    himself
    2.95
    itself
    2.91
     Himself
    2.86
    Activations Density 4.466%

    No Known Activations