INDEX

Explanations

discussions of legal failures and responsibilities

oai_token-act-pair · gemini-2.0-flash

to

np_max-act-logits · gemini-2.0-flash

New Auto-Interp

Configuration

google/gemma-scope-2b-pt-transcoders/layer_22/width_16k/average_l0_15

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.22.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

 textStatus

-0.61

AnchorStyles

-0.58

Matchers

-0.58

 ioutil

-0.57

Sit

-0.54

 rolling

-0.54

WebElementEntity

-0.53

viewDidLoad

-0.52

ROU

-0.52

Datuak

-0.52

POSITIVE LOGITS

 betweenstory

0.54

fromnode

0.50

irtschaft

0.44

瘍

0.43

InSection

0.43

TestingModule

0.43

 exercice

0.43

digkeit

0.42

cmu

0.42

CompilerServices

0.42

Activations Density 1.974%

discussions of legal failures and responsibilities

to

No Comments

No Known Activations