INDEX

Explanations

words or symbols used in programming and coding, especially related to Java and Maven

oai_token-act-pair · gemini-2.0-flash

Mixed language and symbols

np_max-act-logits · gemini-2.0-flash

New Auto-Interp

Configuration

google/gemma-scope-2b-pt-transcoders/layer_25/width_16k/average_l0_41

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.25.ln2.hook_normalized

Architecture

jumprelu_transcoder

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 genoux

-0.79

 fermés

-0.71

ientôt

-0.67

 debout

-0.66

 ouverts

-0.65

 gouttes

-0.65

 réfugi

-0.63

<bos>

-0.61

 connus

-0.60

 couverte

-0.60

POSITIVE LOGITS

Tembelea

0.49

Geplaatst

0.48

Према

0.47

soort

0.44

OND

0.43

BufferException

0.41

lujah

0.40

RK

0.40

ondi

0.40

oric

0.39

Activations Density 1.826%

words or symbols used in programming and coding, especially related to Java and Maven

Mixed language and symbols

No Comments

No Known Activations