INDEX

Explanations

HTML tags, inline styles, and code snippets.

oai_token-act-pair · gemini-2.0-flash

HTML/code

np_max-act · gemini-2.0-flash

New Auto-Interp

Configuration

google/gemma-scope-2b-pt-transcoders/layer_4/width_16k/average_l0_88

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.4.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

 متعلقه

-0.74

NameInMap

-0.74

Демографія

-0.71

 gynhyrchwyd

-0.68

buro

-0.60

 Waray

-0.59

 ویکی‌پدیا

-0.58

LookAnd

-0.57

attenzione

-0.56

rieks

-0.56

POSITIVE LOGITS

 break

0.59

nessed

0.55

 Break

0.54

isateurs

0.50

Break

0.49

DockStyle

0.48

ffiche

0.48

SerializedName

0.47

 BREAK

0.47

breaks

0.47

Activations Density 3.130%

HTML tags, inline styles, and code snippets.

HTML/code

No Comments

No Known Activations