© 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. 21-GEMMASCOPE-TRANSCODER-16K
    7. 5583
    Prev
    Next
    INDEX
    Explanations

    positive adjectives that could be used for evaluation/judgement

    oai_token-act-pair · gemini-2.0-flash

    affirmations or positive remarks

    np_token-act-pair-logits · gpt-4o-mini

    good

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_21/width_16k/average_l0_13
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.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
     >=",
    -0.76
    Personendaten
    -0.54
    SharedDtor
    -0.50
     kasarigan
    -0.49
     great
    -0.49
    DockStyle
    -0.49
     ModelExpression
    -0.49
    jsxFileName
    -0.47
    AutoScaleMode
    -0.44
    balleur
    -0.44
    POSITIVE LOGITS
    تقاوى
    0.73
     point
    0.67
     one
    0.66
     ones
    0.62
    ToPoint
    0.61
    point
    0.59
     thing
    0.57
     thread
    0.57
     lateinit
    0.56
     LiveData
    0.56
    Activations Density 1.822%

    No Known Activations