© 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. 25-GEMMASCOPE-TRANSCODER-16K
    7. 1199
    Prev
    Next
    INDEX
    Explanations

    words in an advertisement for an online gambling site

    oai_token-act-pair · gemini-2.0-flash

    Italian language

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_25/width_16k/average_l0_41
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.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
    发表于
    -0.54
     uska
    -0.49
     للمعارف
    -0.49
    noinspection
    -0.47
     betweenstory
    -0.47
    uurs
    -0.47
    //*/
    -0.46
     actionMode
    -0.46
    كما
    -0.45
    ült
    -0.45
    POSITIVE LOGITS
     ordini
    0.75
     alberi
    0.71
     spagno
    0.68
     specchio
    0.68
     affari
    0.68
     preghi
    0.67
     popoli
    0.67
     movimenti
    0.65
     cappuccio
    0.65
     indipendente
    0.65
    Activations Density 16.226%

    No Known Activations