© 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. 5999
    Prev
    Next
    INDEX
    Explanations

    french words and abbreviations in all capital letters

    oai_token-act-pair · gemini-2.0-flash

    Linux/Ubuntu chat logs

    np_max-act-logits · gemini-2.0-flash

    say "word continuation"

    np_max-act-logits · gpt-5-miniTriggered by @chenshw0109
    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
    rungsseite
    -0.88
     nakalista
    -0.80
    parsedMessage
    -0.76
    styleType
    -0.75
    verwijspagina
    -0.73
    WithIOException
    -0.71
    ⓧ
    -0.70
     BoxFit
    -0.69
    jsonwebtoken
    -0.68
     springfox
    -0.68
    POSITIVE LOGITS
    orologio
    0.85
    escalier
    0.81
    amitié
    0.79
    esistenza
    0.79
    appartamento
    0.77
    esercito
    0.75
    insegna
    0.75
    elenco
    0.74
    horloge
    0.74
    anniversaire
    0.71
    Activations Density 8.387%

    No Known Activations