© 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. 2109
    Prev
    Next
    INDEX
    Explanations

    words related to storytelling within a tragic context

    oai_token-act-pair · gemini-2.0-flash

    Media description

    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
     misión
    -0.55
     Gump
    -0.52
    +#+#
    -0.51
    ISupport
    -0.51
     maniere
    -0.50
     oignon
    -0.49
     Материал
    -0.49
     missão
    -0.48
     zvuky
    -0.48
    hounds
    -0.47
    POSITIVE LOGITS
    StoryboardSegue
    0.78
    TextWatcher
    0.69
     imp
    0.62
    hyrchwyd
    0.62
    MockMvc
    0.56
    Repost
    0.54
    UpInside
    0.54
    Ory
    0.52
    ChildScrollView
    0.51
    stateProvider
    0.51
    Activations Density 3.635%

    No Known Activations