INDEX

Explanations

symbols or special characters within scientific or technical text.

oai_token-act-pair · gemini-2.0-flash

code/scientific snippets

np_max-act-logits · gemini-2.0-flash

New Auto-Interp

Configuration

google/gemma-scope-2b-pt-transcoders/layer_19/width_16k/average_l0_12

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.19.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

 ویکی‌پدی

-0.52

 giao

-0.47

hus

-0.47

pied

-0.43

umen

-0.42

Fio

-0.41

 Nadel

-0.41

ValueStyle

-0.41

esten

-0.40

ins

-0.40

POSITIVE LOGITS

tagHelperRunner

0.78

 onAnimation

0.74

Билгалдахарш

0.68

multirow

0.62

tagHelper

0.60

তথ্যসূত্র

0.59

存于互联网档案馆

0.58

 getItemCount

0.57

 joaat

0.56

первых

0.56

Activations Density 5.512%

symbols or special characters within scientific or technical text.

code/scientific snippets

No Comments

No Known Activations