INDEX

Explanations

Android-related code, mainly the term `InstanceState` and abbreviated journal titles.

oai_token-act-pair · gemini-2.0-flash

InstanceState, Lett

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

<bos>

-0.56

<eos>

-0.52

mer

-0.45

ol

-0.45

’

-0.43

for

-0.42

mer

-0.42

li

-0.42

od

-0.41

POSITIVE LOGITS

 Monfieur

0.70

Efq

0.66

 Jefus

0.64

^(@)

0.63

 Majefty

0.62

 purpoſe

0.61

 myſelf

0.61

 ſeveral

0.60

 pleaſure

0.59

 itſelf

0.59

Activations Density 0.114%

Android-related code, mainly the term `InstanceState` and abbreviated journal titles.

InstanceState, Lett

No Comments

No Known Activations

Android-related code, mainly the term `InstanceState` and abbreviated journal titles.

InstanceState, Lett

No Comments

No Known Activations