© 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. 0-GEMMASCOPE-TRANSCODER-16K
    7. 7774
    Prev
    Next
    INDEX
    Explanations

    the word "directions"

    oai_token-act-pair · gemini-2.0-flash

    directions

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_0/width_16k/average_l0_76
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.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
     démo
    -0.63
     achet
    -0.57
    WriteLiteral
    -0.57
     automatiques
    -0.53
     immédi
    -0.52
    getMenuInflater
    -0.50
     suivantes
    -0.49
     eletrônico
    -0.49
     aikana
    -0.49
     normaux
    -0.49
    POSITIVE LOGITS
     تضيفلها
    0.71
    ########.
    0.69
    TagHelper
    0.68
    >';
    0.68
     φ
    0.67
    gamesh
    0.67
    aktery
    0.64
    >';
    0.63
     sesu
    0.62
    Truly
    0.61
    Activations Density 1.541%

    No Known Activations