© 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. 8604
    Prev
    Next
    INDEX
    Explanations

    nouns and adjectives used to describe places or people

    oai_token-act-pair · gemini-2.0-flash

    say apostrophe

    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
     démocr
    -1.37
     avoient
    -1.34
     charité
    -1.29
     fermés
    -1.26
     sauvages
    -1.26
     supérieurs
    -1.25
     vectorielles
    -1.23
     automatiques
    -1.23
     étoient
    -1.21
     ProtoMessage
    -1.21
    POSITIVE LOGITS
     ‘
    1.28
    ‘
    1.22
     '
    1.19
    ’
    1.16
    ”
    1.10
    '
    1.09
     ’
    0.96
    ’,
    0.92
    "
    0.92
    ,’
    0.89
    Activations Density 5.020%

    No Known Activations