© 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. 4057
    Prev
    Next
    INDEX
    Explanations

    references to things that you can see in a mirror

    oai_token-act-pair · gemini-2.0-flash

    reflection, accuracy, evaluation

    np_max-act-logits · gemini-2.0-flash
    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
     reflection
    -2.59
     reflect
    -2.56
     reflecting
    -2.52
     Reflect
    -2.50
     reflective
    -2.45
     reflected
    -2.41
    reflect
    -2.38
     Reflection
    -2.34
     reflects
    -2.33
     reflections
    -2.31
    POSITIVE LOGITS
     صوتيه
    0.66
    วง
    0.48
    canakan
    0.47
     дописавши
    0.47
     Auvergne
    0.47
     vore
    0.46
     simplifié
    0.44
    illies
    0.44
     TextInputType
    0.43
    èce
    0.43
    Activations Density 3.221%

    No Known Activations