INDEX

Explanations

language describing experimental results

oai_token-act-pair · gemini-2.0-flash

code/research

np_max-act-logits · gemini-2.0-flash

New Auto-Interp

Configuration

google/gemma-scope-2b-pt-transcoders/layer_24/width_16k/average_l0_37

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.24.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

 autorytatywna

-0.71

 pleaſure

-0.65

 Wikimedia

-0.61

celes

-0.61

 الرياضيه

-0.60

хьтан

-0.60

 Wartawan

-0.60

IsMutable

-0.59

 Samaria

-0.58

 JpaRepository

-0.58

POSITIVE LOGITS

ரும்

0.47

ButtonStyle

0.47

iti

0.45

出版年

0.45

onViewCreated

0.44

 partita

0.43

 nakalista

0.42

pos

0.42

Péri

0.42

PDC

0.40

Activations Density 7.625%

language describing experimental results

code/research

No Comments

No Known Activations