INDEX

Explanations

Polish place names or words ending in 'ien'

oai_token-act-pair · gemini-2.0-flash

Poland

np_max-act-logits · gemini-2.0-flash

New Auto-Interp

Configuration

google/gemma-scope-2b-pt-transcoders/layer_23/width_16k/average_l0_25

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.23.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

inf

-0.46

et

-0.45

bute

-0.44

als

-0.43

Par

-0.43

aturing

-0.43

mery

-0.43

di

-0.43

 config

-0.43

-0.42

POSITIVE LOGITS

 purpoſe

0.88

ſelves

0.85

 Majefty

0.85

 endwhile

0.83

Efq

0.83

 reaſon

0.82

 poffible

0.82

 iſt

0.81

WebVitals

0.81

ſelf

0.79

Activations Density 0.717%

Polish place names or words ending in 'ien'

Poland

No Comments

No Known Activations