INDEX

Explanations

email addresses and file extensions

oai_token-act-pair · gemini-2.0-flash

edu

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

edu

-1.89

edu

-1.20

EDU

-0.98

Edu

-0.81

<bos>

-0.73

Edu

-0.69

EDU

-0.68

########.

-0.54

 Univ

-0.53

gov

-0.50

POSITIVE LOGITS

AddTagHelper

0.62

"',

0.55

CodeAnalysis

0.54

ılık

0.49

itaria

0.49

Namespaces

0.48

ppling

0.48

:]:

0.48

csrf

0.48

AndPassword

0.47

Activations Density 3.245%

email addresses and file extensions

edu

No Comments

No Known Activations