INDEX

Explanations

words and phrases related to opinion, belief, and expression

oai_token-act-pair · gemini-2.0-flash

Miscellaneous topics

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

IContainer

-0.58

 Monfieur

-0.57

IsMutable

-0.56

SpringBootTest

-0.55

 tartalomajánló

-0.55

httphttps

-0.52

 Signalez

-0.51

">@

-0.49

 myſelf

-0.49

 confirmer

-0.49

POSITIVE LOGITS

igshid

0.50

<bos>

0.49

 Newswire

0.48

createComponent

0.45

 bezeichneter

0.45

 BoxFit

0.45

medriver

0.44

LinkId

0.44

FRANC

0.44

figer

0.44

Activations Density 59.019%

words and phrases related to opinion, belief, and expression

Miscellaneous topics

No Comments

No Known Activations