INDEX

Explanations

grammatical words and descriptive words in German

oai_token-act-pair · gemini-2.0-flash

non-english languages

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

ьаж

-0.49

 Forever

-0.47

Else

-0.46

Turn

-0.45

turn

-0.43

 Linger

-0.41

XtraEditors

-0.40

Forever

-0.40

 Else

-0.40

 Deja

-0.39

POSITIVE LOGITS

 bezeichneter

0.86

EDEFAULT

0.72

 correctes

0.71

__*/

0.68

픈

0.67

קישורים

0.65

findpost

0.64

__":

0.63

 berjudul

0.62

inguém

0.61

Activations Density 0.092%

grammatical words and descriptive words in German

non-english languages

No Comments

No Known Activations