INDEX

Explanations

snippets of code containing parentheses, array notation, and the word "To"

oai_token-act-pair · gemini-2.0-flash

open parenthesis

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

 kasarigan

-0.72

setVerticalGroup

-0.60

extAlignment

-0.56

MessageState

-0.56

 "..\..\..\

-0.53

ParallelGroup

-0.53

Vanjske

-0.53

ftagPool

-0.52

اجة

-0.52

Życiorys

-0.52

POSITIVE LOGITS

GEBURTSDATUM

0.60

كتشاف

0.54

 República

0.53

 gyhoeddwyd

0.52

 brune

0.51

 staking

0.50

 Puch

0.49

 Lott

0.47

erover

0.47

Коро

0.47

Activations Density 3.460%

snippets of code containing parentheses, array notation, and the word "To"

open parenthesis

No Comments

No Known Activations