© 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. 8-GEMMASCOPE-TRANSCODER-16K
    7. 480
    Prev
    Next
    INDEX
    Explanations

    scientific studies and meta-analyses

    oai_token-act-pair · gemini-2.0-flash

    identifying and including

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_8/width_16k/average_l0_52
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.8.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
     bite
    -0.48
     gang
    -0.47
    ib
    -0.43
    gaz
    -0.43
    cele
    -0.42
     Raj
    -0.42
    gang
    -0.42
    ষ্
    -0.42
     di
    -0.41
     Sol
    -0.41
    POSITIVE LOGITS
     Roskov
    1.06
    ValueStyle
    1.05
     ujednoznacz
    0.86
     صوتيه
    0.82
    تقاوى
    0.71
    InvalidProtocol
    0.71
    曖昧さ回避
    0.69
    TintMode
    0.69
    Aktualisiert
    0.68
     AttributeSet
    0.68
    Activations Density 3.938%

    No Known Activations