© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 19-GEMMASCOPE-TRANSCODER-16K
    7. 5805
    Prev
    Next
    INDEX
    Explanations

    words, pronouns, and phrases used to compare, contrast or reference subjects within a text

    oai_token-act-pair · gemini-2.0-flash

    Refers to multiple things

    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
     StringTokenizer
    -0.51
    ętr
    -0.49
     JpaRepository
    -0.48
     חיצוניים
    -0.48
     समीक्षक
    -0.47
     مشين
    -0.47
    ⓧ
    -0.47
     GenerationType
    -0.45
     विश्वसनीयता
    -0.45
    principalColumn
    -0.44
    POSITIVE LOGITS
    <bos>
    0.68
     aspect
    0.57
     désolés
    0.55
     thing
    0.53
     aspects
    0.50
    vesti
    0.48
    Geplaatst
    0.48
     disambiguazione
    0.48
    IVIA
    0.48
    chini
    0.47
    Activations Density 5.752%

    No Known Activations