© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 24-GEMMASCOPE-TRANSCODER-16K
    7. 8513
    Prev
    Next
    INDEX
    Explanations

    words or phrases related to video advertising and data-driven targeting

    oai_token-act-pair · gemini-2.0-flash

    advertising

    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
    Personendaten
    -1.06
    +#+#
    -0.86
    ftagPool
    -0.84
    帖最后由
    -0.79
    webElementXpaths
    -0.78
    Hentet
    -0.78
    @[+][
    -0.77
    Geplaatst
    -0.76
     @"/
    -0.73
    awtextra
    -0.71
    POSITIVE LOGITS
     fondation
    0.45
    enoord
    0.44
    rante
    0.43
    apo
    0.41
    eros
    0.41
    مو
    0.41
     apparence
    0.41
    erty
    0.40
    poo
    0.40
    مان
    0.40
    Activations Density 3.015%

    No Known Activations