INDEX

Explanations

words related to medical studies and cancer, especially breast and colorectal cancer

oai_token-act-pair · gemini-2.0-flash

random punctuation and non-english text

np_token-act-pair-logits · gemini-2.0-flash

cancer research

np_max-act-logits · gemini-2.0-flash

New Auto-Interp

Configuration

google/gemma-scope-2b-pt-transcoders/layer_16/width_16k/average_l0_10

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.16.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

WebVitals

-0.51

pandora

-0.50

PROV

-0.49

 vnder

-0.49

isole

-0.48

reathe

-0.46

 endwhile

-0.44

 Greenwood

-0.44

プロ

-0.44

洋

-0.44

POSITIVE LOGITS



0.56

)['

0.54

BibitemShut

0.53

الحياه

0.52

PasswordEncoder

0.50

checkable

0.49

ViewImports

0.49

ंदीखरीदारी

0.48

Espèce

0.48

DeleteBehavior

0.48

Activations Density 2.105%

words related to medical studies and cancer, especially breast and colorectal cancer

random punctuation and non-english text

cancer research

No Comments

No Known Activations