© 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. 4-GEMMASCOPE-TRANSCODER-16K
    7. 1914
    Prev
    Next
    INDEX
    Explanations

    personal relationships, location or time with personal pronouns

    oai_token-act-pair · gemini-2.0-flash

    personal stories

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_4/width_16k/average_l0_88
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.4.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
     Empieza
    -0.56
     históricas
    -0.51
     professionali
    -0.48
     boucles
    -0.47
     compréhen
    -0.46
    ochlor
    -0.46
    ⓧ
    -0.45
     nødvendig
    -0.45
     agrícolas
    -0.45
     comunicazione
    -0.45
    POSITIVE LOGITS
    DockStyle
    0.67
     تضيفلها
    0.61
    setVerticalGroup
    0.58
    orteur
    0.58
     vPvB
    0.56
    ',{
    0.56
    ConstraintMaker
    0.56
    TAINER
    0.56
    TemporalType
    0.54
    Obrázky
    0.53
    Activations Density 0.702%

    No Known Activations