© 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. 24-GEMMASCOPE-TRANSCODER-16K
    7. 4479
    Prev
    Next
    INDEX
    Explanations

    text from a news article where a person's name and title are mentioned and also text related to police

    oai_token-act-pair · 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
    +#+#
    -1.06
    tvguidetime
    -0.93
    RegressionTest
    -0.91
    abestanden
    -0.76
    MENAFN
    -0.73
    RTLD
    -0.72
     Roskov
    -0.71
     CreateTagHelper
    -0.69
     Italijanski
    -0.69
     оригіналу
    -0.69
    POSITIVE LOGITS
    bode
    0.49
    PostMapping
    0.45
    vor
    0.43
    体
    0.42
     przes
    0.42
    retum
    0.42
    JTextArea
    0.42
    itie
    0.42
    aclk
    0.41
    berton
    0.41
    Activations Density 2.078%

    No Known Activations