INDEX

Explanations

the word "the"

oai_token-act-pair · gemini-2.0-flash

the

np_max-act-logits · gemini-2.0-flash

New Auto-Interp

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

انيف

-0.79

Hochspringen

-0.71

)}</

-0.71

úrese

-0.70

tagHelperRunner

-0.70

extAlignment

-0.68

"]="

-0.66

SOUNDBITE

-0.65

 חיצוניים

-0.65

</thead>

-0.64

POSITIVE LOGITS

 Stallion

0.45

 pince

0.43

 generales

0.43

 bankası

0.42

 devoirs

0.41

 rút

0.40

 Baillargeon

0.40

 puffs

0.40

東大

0.39

 pumps

0.39

Activations Density 1.994%

the word "the"

the

No Comments

No Known Activations