INDEX

Explanations

words and short phrases indicating actions or processes.

oai_token-act-pair · gemini-2.0-flash

-ing verbs

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

contentLoaded

-0.58

htaccess

-0.55

alnız

-0.55

__*/

-0.53

ifred

-0.52

Gön

-0.52

testens

-0.52

cripción

-0.52

vocable

-0.51

ỡng

-0.51

POSITIVE LOGITS

TagHelper

0.65

Portale

0.56

########.

0.54

OGND

0.51

ClCompile

0.50

 оригіналу

0.49

RenderAtEndOf

0.49

vergleich

0.48

capture

0.48

 initComponents

0.48

Activations Density 1.577%

words and short phrases indicating actions or processes.

-ing verbs

No Comments

No Known Activations