INDEX

Explanations

various function words in different languages, and appears to key in on conjunctions and "I" statements.

oai_token-act-pair · gemini-2.0-flash

Violent/Aggressive sentiment

np_max-act · gemini-2.0-flash

New Auto-Interp

Configuration

google/gemma-scope-2b-pt-transcoders/layer_8/width_16k/average_l0_52

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.8.ln2.hook_normalized

Architecture

jumprelu_transcoder

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

IntoConstraints

-0.56

ofed

-0.50

 évêque

-0.49

decin

-0.49

expandindo

-0.49

 soeur

-0.48

libro

-0.48

ributors

-0.47

 sœur

-0.47

ơ

-0.47

POSITIVE LOGITS

CodeAttribute

0.64

}")]

0.57

 Numerade

0.56

下载附件

0.54

>{@

0.53

 Administrativna

0.53

 typelib

0.53

 VIAF

0.52

 BoxFit

0.50

Koordinaten

0.50

Activations Density 0.129%

various function words in different languages, and appears to key in on conjunctions and "I" statements.

Violent/Aggressive sentiment

No Comments

No Known Activations