© 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. 24-GEMMASCOPE-TRANSCODER-16K
    7. 4667
    Prev
    Next
    INDEX
    Explanations

    content related to blogs and other informal writing.

    oai_token-act-pair · gemini-2.0-flash

    its

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_24/width_16k/average_l0_37
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.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
    antu
    -0.44
     elä
    -0.40
     themselves
    -0.40
    tablir
    -0.40
    InjectMocks
    -0.39
    Comma
    -0.39
     löytyy
    -0.38
     himself
    -0.38
    شون
    -0.37
     olduk
    -0.36
    POSITIVE LOGITS
     its
    3.56
    Its
    3.25
     Its
    3.08
    its
    2.75
     Оно
    2.16
    它的
    2.05
     ITS
    1.90
    ITS
    1.82
     оно
    1.56
    因为它
    1.43
    Activations Density 13.468%

    No Known Activations