INDEX

Explanations

words used in technical documents to express planning, likelihood, responsibility, or errors.

oai_token-act-pair · gemini-2.0-flash

errors and fixes

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

okhttp

-0.54

利

-0.51

eken

-0.48

makeConstraints

-0.48

assertNull

-0.47

 NDEBUG

-0.45

andExpect

-0.44

 što

-0.44

 Tang

-0.44

交代

-0.43

POSITIVE LOGITS

脚注の使い方

0.58

 StatefulWidget

0.58

PreferredItem

0.56

 nakalista

0.56

 насељу

0.54

 calendriers

0.53

Personendaten

0.53

出版年

0.52

liceerd

0.52

utilisons

0.51

Activations Density 8.000%

words used in technical documents to express planning, likelihood, responsibility, or errors.

errors and fixes

No Comments

No Known Activations