INDEX

Explanations

words and characters associated with programming languages and/or Portuguese

oai_token-act-pair · gemini-2.0-flash

non-English language text

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

 quelli

-0.58

ruptedException

-0.56

 itself

-0.47

 kurie

-0.46

 שונים

-0.44

ców

-0.43

 רבים

-0.42

 duomen

-0.40

its

-0.40

ITS

-0.40

POSITIVE LOGITS

 himſelf

0.82

 Majefty

0.79

makeConstraints

0.73

 חיצוני

0.68

SequentialGroup

0.67

Efq

0.65

 myſelf

0.64

 houſe

0.63

 elles

0.63

 ellas

0.61

Activations Density 0.098%

words and characters associated with programming languages and/or Portuguese

non-English language text

No Comments

No Known Activations