© 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. 14611
    Prev
    Next
    INDEX
    Explanations

    words that categorize stories, like 'thriller', 'tale', 'adventure'

    oai_token-act-pair · gemini-2.0-flash

    stories and games

    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
     immédi
    -0.53
    rshire
    -0.53
    NewUrlParser
    -0.49
     TimeUnit
    -0.48
     käns
    -0.45
    Configurer
    -0.45
    colgroup
    -0.45
     inmediata
    -0.44
    ốn
    -0.44
    NgModule
    -0.44
    POSITIVE LOGITS
    ModelSerializer
    0.59
    évaluateur
    0.58
    ⓘ
    0.58
    SharedDtor
    0.57
    ाहरण
    0.56
    فایل‌لار
    0.56
    brtc
    0.56
    protoc
    0.55
     שוליים
    0.55
    WireFormatLite
    0.54
    Activations Density 1.610%

    No Known Activations