© 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. 24-GEMMASCOPE-TRANSCODER-16K
    7. 11698
    Prev
    Next
    INDEX
    Explanations

    text describing how a company manages vendors for a client

    oai_token-act-pair · gemini-2.0-flash

    problems and failures

    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
    RenderAtEndOf
    -0.79
    @[+][
    -0.76
     Theſe
    -0.75
     FetchType
    -0.73
    TargetException
    -0.72
     ſame
    -0.69
    клопе
    -0.69
     ſta
    -0.67
    PerformLayout
    -0.66
    Brainz
    -0.66
    POSITIVE LOGITS
    resave
    0.42
     down
    0.39
    achuca
    0.38
    producer
    0.38
     suất
    0.36
     producer
    0.35
     n
    0.35
     host
    0.35
    dbo
    0.35
    
    0.35
    Activations Density 2.255%

    No Known Activations