INDEX

Explanations

time durations with hours and minutes

oai_token-act-pair · gemini-2.0-flash

numerical measurements

np_max-act-logits · gemini-2.0-flash

New Auto-Interp

Configuration

google/gemma-scope-2b-pt-transcoders/layer_20/width_16k/average_l0_11

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.20.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

 "));

-0.62

kháu

-0.52

 subunits

-0.50

SharedDtor

-0.50

MENAFN

-0.48

Демографія

-0.47

 externi

-0.47

EndGlobalSection

-0.46

 Approx

-0.45

omé

-0.45

POSITIVE LOGITS

ंदीखरीदारी

0.63

numerusform

0.61

MemoryWarning

0.58

multer

0.57

WriteTagHelper

0.56

SequentialGroup

0.56

ImageContext

0.55

 CanadaChoose

0.50

 חיצוניים

0.50

 виправивши

0.49

Activations Density 4.298%

time durations with hours and minutes

numerical measurements

No Comments

No Known Activations