INDEX

Explanations

words related to consequences and outcomes

oai_token-act-pair · gemini-2.0-flash

say "of"

np_max-act-logits · gemini-2.0-flash

New Auto-Interp

Configuration

google/gemma-scope-2b-pt-transcoders/layer_20/width_16k/average_l0_11

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.20.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

 della

-0.88

del

-0.85

 dell

-0.79

des

-0.75

 dello

-0.70

 ofthe

-0.69

ofthe

-0.68

du

-0.68

 της

-0.66

 degli

-0.65

POSITIVE LOGITS

parsedMessage

1.07

LookAnd

1.05

extAlignment

1.00

RenderAtEndOf

0.99

 nonatomic

0.96

 gynhyrchwyd

0.95

 समीक्षाओं

0.95

DoubleQuotes

0.94

 CreateTagHelper

0.93

 <=",

0.93

Activations Density 1.523%

words related to consequences and outcomes

say "of"

No Comments

No Known Activations