INDEX

Explanations

articles of clothing described with adjectives like "sassy" and "adorable", and words like "with" and "and"

oai_token-act-pair · gemini-2.0-flash

miscellaneous text

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

تقاوى

-0.83

 виправивши

-0.78

rungsseite

-0.78

parsedMessage

-0.76

IntoConstraints

-0.73

MessageOf

-0.72

期刊论文

-0.71

AnchorStyles

-0.71

windowFixed

-0.71

Lähteet

-0.71

POSITIVE LOGITS

Ag

0.43

 figure

0.42

수

0.41

le

0.40

nested

0.40

нье

0.38

Moody

0.38

rs

0.38

LEncoder

0.37

 Pneum

0.37

Activations Density 1.090%

articles of clothing described with adjectives like "sassy" and "adorable", and words like "with" and "and"

miscellaneous text

No Comments

No Known Activations