INDEX

Explanations

dates and date ranges with some surrounding context.

oai_token-act-pair · gemini-2.0-flash

year ranges

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

pronounced

-0.50

Seasons

-0.50

falen

-0.50

wyt

-0.47

veyor

-0.47

scene

-0.45

Scoop

-0.45

ceğini

-0.45

emate

-0.45

 trương

-0.44

POSITIVE LOGITS

 transfieras

0.75

 referenties

0.74

TestingModule

0.68

AndEndTag

0.66

 المعيارى

0.63

 محفوظة

0.62

fjspx

0.60

 HasFactory

0.60

XmlAccessType

0.59

❉

0.59

Activations Density 12.758%

dates and date ranges with some surrounding context.

year ranges

No Comments

No Known Activations