INDEX

Explanations

long sentences that enumerate advantages in technical documents (possibly patent applications).

oai_token-act-pair · gemini-2.0-flash

improvements and efficiency

np_max-act-logits · gemini-2.0-flash

New Auto-Interp

Configuration

google/gemma-scope-2b-pt-transcoders/layer_20/width_16k/average_l0_11

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.20.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

 Theſe

-0.63

 ddelweddau

-0.61

Handlung

-0.57

 препратки

-0.56

csolódó

-0.56

phazard

-0.56

SpringBootTest

-0.56

 natale

-0.55

 uſed

-0.55

 кӀош

-0.54

POSITIVE LOGITS

 easier

0.57

MLLoader

0.54

########.

0.53

 longer

0.49

ticides

0.49

 shorter

0.47

ertos

0.46

LikeLiked

0.46

easier

0.46

no

0.46

Activations Density 4.402%

long sentences that enumerate advantages in technical documents (possibly patent applications).

improvements and efficiency

No Comments

No Known Activations