INDEX

Explanations

words and symbols pertaining to mathematics, scientific research, legal or technical writing, and specific, documented facts

oai_token-act-pair · gemini-2.0-flash

Science and age in math

np_max-act · gemini-2.0-flash

New Auto-Interp

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

momix

-0.55

setViewportView

-0.52

(>

-0.52

cobacterium

-0.52

vester

-0.51

GEBURTSDATUM

-0.50

ostomy

-0.50

ValueStyle

-0.49

 AssemblyProduct

-0.49

pflich

-0.49

POSITIVE LOGITS

(<

0.80

 minimized

0.68

 Minimize

0.66

 minimizes

0.65

 geringe

0.63

 reduced

0.62

 minimizing

0.61

 diminutive

0.60

 minimize

0.60

 Reduced

0.60

Activations Density 31.172%

words and symbols pertaining to mathematics, scientific research, legal or technical writing, and specific, documented facts

Science and age in math

No Comments

No Known Activations