© 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. 7802
    Prev
    Next
    INDEX
    Explanations

    words and phrases related to results and establishing a default

    oai_token-act-pair · gemini-2.0-flash

    non-english text

    np_max-act · gemini-2.0-flash

    Spanish/Portuguese suffixes

    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_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
    ificada
    -0.88
    ucción
    -0.87
    ônica
    -0.85
    osidad
    -0.85
    ônico
    -0.84
    sividad
    -0.81
    cepción
    -0.79
    acidade
    -0.77
    tabilidade
    -0.77
    bilidad
    -0.77
    POSITIVE LOGITS
     itſelf
    1.27
     ―――――
    1.23
    ⓧ
    1.17
     Efq
    1.16
    parsedMessage
    1.16
     defaultstate
    1.16
     ſind
    1.16
     ་་
    1.15
     Meksiku
    1.13
     tartalomajánló
    1.13
    Activations Density 1.365%

    No Known Activations