INDEX

Explanations

mentions of countries, territories, or national origin, often in a legal or demographic context.

oai_token-act-pair · gemini-2.0-flash

country

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

 Conſ

-0.68

+#+

-0.68

 Reſ

-0.68

 pleaſure

-0.66

PointerException

-0.66

 "$@"

-0.66

protoimpl

-0.65

 Achter

-0.64

 ſen

-0.63

 ſeveral

-0.62

POSITIVE LOGITS

InstanceState

0.53

0.45

mender

0.40

’

0.40

al

0.38

herald

0.38

batore

0.37

ValueStyle

0.37

tem

0.37

as

0.36

Activations Density 10.276%

mentions of countries, territories, or national origin, often in a legal or demographic context.

country

No Comments

No Known Activations