INDEX

Explanations

the word 'area' and words related to data and locations.

oai_token-act-pair · gemini-2.0-flash

area

np_max-act · gemini-2.0-flash

New Auto-Interp

Configuration

google/gemma-scope-2b-pt-transcoders/layer_0/width_16k/average_l0_76

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.0.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

 Theſe

-1.43

Efq

-1.43

 themſelves

-1.41

 itſelf

-1.33

 whoſe

-1.29

 myſelf

-1.29

$_"

-1.27

 Majefty

-1.23

 ſeveral

-1.23

 Anſ

-1.22

POSITIVE LOGITS

0.67

 оригіналу

0.67

requestCode

0.65

0.63

rawDesc

0.62

and

0.61

VideoCapture

0.60

is

0.60

readystatechange

0.60

Activations Density 1.949%

the word 'area' and words related to data and locations.

area

No Comments

No Known Activations