INDEX

Explanations

transition words like "then", "therefore", and "further"

oai_token-act-pair · gemini-2.0-flash

then

np_max-act · gemini-2.0-flash

New Auto-Interp

Configuration

google/gemma-scope-2b-pt-transcoders/layer_2/width_16k/average_l0_49

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.2.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

 then

-1.09

 Then

-0.86

Then

-0.79

then

-0.76

 THEN

-0.72

THEN

-0.67

poi

-0.55

然后

-0.53

 ثم

-0.52

 Roskov

-0.52

POSITIVE LOGITS

Efq

0.96

 uſed

0.94

expandindo

0.92

 Monfieur

0.89

 Theſe

0.89

 Anſ

0.89

 myſelf

0.88

 ſta

0.88

 whoſe

0.88

 Houſe

0.88

Activations Density 0.186%

transition words like "then", "therefore", and "further"

then

No Comments

No Known Activations