INDEX

Explanations

words and phrases having to do with time and location

oai_token-act-pair · gemini-2.0-flash

past

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

 Gaylord

-0.55

ROIT

-0.49

 AttributeSet

-0.46

 platt

-0.46

upol

-0.46

 Alamo

-0.43

 arşivlendi

-0.43

zboi

-0.43

 whole

-0.43

 Público

-0.42

POSITIVE LOGITS

MigrationBuilder

0.84

 BoxFit

0.80

ValueStyle

0.79

 tartalomajánló

0.73

reszcie

0.69

ंदीखरीदारी

0.68

 ProtoMessage

0.67

FormUrlEncoded

0.65

"));

0.65

anglès

0.65

Activations Density 1.567%

words and phrases having to do with time and location

past

No Comments

No Known Activations