INDEX

Explanations

dates and numbers associated with a timeline or duration of events

oai_token-act-pair · gemini-2.0-flash

time spans

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

sel

-0.53

Sel

-0.49

readValue

-0.47

bek

-0.45

会话

-0.45

 tomorrow

-0.45

ORROW

-0.44

 overnight

-0.43

ad

-0.43

 enca

-0.43

POSITIVE LOGITS

 resourceCulture

0.79

 varandra

0.75

AddTagHelper

0.71

 Taktlose

0.71

 ويكيپيديا

0.66

tanleria

0.66

AndEndTag

0.63

 itſelf

0.63

 généraux

0.62

 stället

0.62

Activations Density 14.812%

dates and numbers associated with a timeline or duration of events

time spans

No Comments

No Known Activations