© 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. 10714
    Prev
    Next
    INDEX
    Explanations

    text blocks in an argumentative essay.

    oai_token-act-pair · gemini-2.0-flash

    negative arguments

    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
     NSCoder
    -0.44
     lost
    -0.44
     aidant
    -0.43
    чё
    -0.42
    [`
    -0.42
     loses
    -0.41
     Mur
    -0.40
     Popular
    -0.39
     minder
    -0.39
     Hush
    -0.38
    POSITIVE LOGITS
    MLLoader
    0.69
     فريبيس
    0.68
    unknownFields
    0.66
     judiciaire
    0.66
    IsContent
    0.65
    fromnode
    0.65
    onViewCreated
    0.64
    Personendaten
    0.64
    sizeCache
    0.63
    BufferException
    0.62
    Activations Density 5.693%

    No Known Activations