INDEX

Explanations

proper nouns that could refer to places or organizations.

oai_token-act-pair · gemini-2.0-flash

average

np_max-act · gemini-2.0-flash

New Auto-Interp

Configuration

google/gemma-scope-2b-pt-transcoders/layer_0/width_16k/average_l0_76

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.0.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

 bross

-0.58

 podjet

-0.52

mę

-0.50

Démographie

-0.49

หว

-0.49

dė

-0.49

achie

-0.49

 Défense

-0.49

-0.47

 glaubt

-0.47

POSITIVE LOGITS

verwijspagina

0.78

MemoryWarning

0.75

Geplaatst

0.75

sidemargin

0.71

StandardCharsets

0.68

putc

0.67

swick

0.67

 Forumite

0.66

 Britannica

0.65

toplankton

0.64

Activations Density 0.973%

proper nouns that could refer to places or organizations.

average

No Comments

No Known Activations