INDEX

Explanations

questions with potential answers

oai_token-act-pair · gemini-2.0-flash

language

np_token-act-pair-logits · gemini-2.0-flash

English language

np_max-act-logits · gemini-2.0-flash

New Auto-Interp

Configuration

google/gemma-scope-2b-pt-transcoders/layer_16/width_16k/average_l0_10

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.16.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

 صوتيه

-0.79

Efq

-0.73

 Reſ

-0.66

 ſmall

-0.66

GEBURTSDATUM

-0.65

 ſche

-0.65

солю

-0.65

 purpoſe

-0.62

 itſelf

-0.62

 calculées

-0.60

POSITIVE LOGITS

 language

0.53

 Language

0.52

Sent

0.52

 word

0.51

word

0.51

 English

0.49

ENGLISH

0.49

 Grammar

0.48

Word

0.47

LANGUAGE

0.47

Activations Density 1.471%

questions with potential answers

language

English language

No Comments

No Known Activations