INDEX

Explanations

non-English characters within the English text

oai_token-act-pair · gemini-2.0-flash

Code and special characters

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

WithIOException

-0.62

=$?

-0.60

الإنجليزية

-0.59

帖最后由

-0.57

ünst

-0.54

TextNode

-0.54

jazdu

-0.53

__["

-0.52

ltä

-0.51

endpush

-0.50

POSITIVE LOGITS

complexType

0.62

UnitTesting

0.53

 الحره

0.52

mybatisplus

0.51

ynchronously

0.44

LayoutStyle

0.43

 للاسماء

0.40

JsonProperty

0.39

randomUUID

0.39

 Hymen

0.38

Activations Density 0.542%

non-English characters within the English text

Code and special characters

No Comments

No Known Activations