© 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. 22-GEMMASCOPE-TRANSCODER-16K
    7. 6870
    Prev
    Next
    INDEX
    Explanations

    words that appear professional and analytical

    oai_token-act-pair · gemini-2.0-flash

    are

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_22/width_16k/average_l0_15
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.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
    are
    -0.44
    -
    -0.43
    he
    -0.38
     were
    -0.38
     are
    -0.38
     have
    -0.36
    A
    -0.35
    have
    -0.35
    muerzo
    -0.34
    h
    -0.34
    POSITIVE LOGITS
     Jefus
    1.12
     EconPapers
    1.10
     Efq
    1.09
    \{\\
    1.05
    Jereo
    0.99
     disambiguazione
    0.99
     beginnetje
    0.99
     initComponents
    0.98
     Majefty
    0.98
    TestingModule
    0.97
    Activations Density 6.459%

    No Known Activations