INDEX

Explanations

words or short phrases that indicate uncertainty

oai_token-act-pair · gemini-2.0-flash

least/as

np_max-act · gemini-2.0-flash

New Auto-Interp

Configuration

google/gemma-scope-2b-pt-transcoders/layer_7/width_16k/average_l0_70

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.7.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

 Theſe

-0.71

httphttps

-0.69

(!__

-0.68

ConstraintMaker

-0.65

 nahilalakip

-0.63

 myſelf

-0.62

 Beſ

-0.61

 kasarigan

-0.61

expandindo

-0.61

fjspx

-0.61

POSITIVE LOGITS

ჩ

0.48

OGND

0.47

 Weekend

0.44

 Elekt

0.44

cetamol

0.44

èrement

0.43

rawDesc

0.43

AutoScale

0.42

"{

0.42

 weekend

0.42

Activations Density 2.406%

words or short phrases that indicate uncertainty

least/as

No Comments

No Known Activations