INDEX

Explanations

phrases related to obligation and sacrifice

oai_token-act-pair · gemini-2.0-flash

going to any lengths

np_max-act-logits · gemini-2.0-flash

New Auto-Interp

Configuration

google/gemma-scope-2b-pt-transcoders/layer_19/width_16k/average_l0_12

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.19.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

InjectAttribute

-0.60

 invokingState

-0.52

contentLoaded

-0.52

parsedMessage

-0.52

yet

-0.50

 אז

-0.45

 Тогда

-0.44

__((

-0.44

 îles

-0.42

echos

-0.42

POSITIVE LOGITS

 anything

0.96

 Anything

0.92

Anything

0.89

 ANYTHING

0.87

 lengths

0.86

anything

0.85

 Sacrific

0.66

 MaterialApp

0.61

 sacrificed

0.60

minton

0.60

Activations Density 0.494%

phrases related to obligation and sacrifice

going to any lengths

No Comments

No Known Activations