© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 25-GEMMASCOPE-TRANSCODER-16K
    7. 9788
    Prev
    Next
    INDEX
    Explanations

    substrings containing possessive pronouns along with body parts and some crime concepts

    oai_token-act-pair · gemini-2.0-flash

    body parts

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_25/width_16k/average_l0_41
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.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
    StoreMessageInfo
    -0.52
    fasis
    -0.48
    Tikang
    -0.46
    󠁢
    -0.46
    кономі
    -0.46
     keş
    -0.45
     TMPro
    -0.45
    coltà
    -0.44
     Repeat
    -0.44
    postmedia
    -0.44
    POSITIVE LOGITS
    IntoConstraints
    0.77
    CloseOperation
    0.77
    :✨
    0.68
    TagMode
    0.62
    LookAnd
    0.57
    uxxxx
    0.56
    はじめに
    0.56
     jugs
    0.52
     arm
    0.51
    Hozzáférés
    0.51
    Activations Density 5.039%

    No Known Activations