Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-2-2B
    3. 22-GEMMASCOPE-TRANSCODER-16K
    4. 14494
    Prev
    Next
    INDEX
    Explanations

    hexadecimal color codes

    oai_token-act-pair · gemini-2.0-flash

    0

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_22/width_16k/average_l0_15
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.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
    PMailer
    -0.61
    ElementException
    -0.60
     typelib
    -0.53
    toupper
    -0.52
    bewerken
    -0.49
    やら
    -0.49
    GenerationType
    -0.49
     виправивши
    -0.48
    Према
    -0.48
    fgets
    -0.48
    POSITIVE LOGITS
     étoient
    0.64
     saveiro
    0.61
     avoient
    0.60
     paſſ
    0.59
     auroit
    0.58
     vixion
    0.57
     feroit
    0.56
     démocr
    0.56
     qashqai
    0.56
    ználat
    0.55
    Activations Density 2.547%

    No Known Activations