INDEX

Explanations

tokens used commonly in online forum or user-generated content

oai_token-act-pair · gemini-2.0-flash

apostrophes

np_max-act · gemini-2.0-flash

New Auto-Interp

Configuration

google/gemma-scope-2b-pt-transcoders/layer_8/width_16k/average_l0_52

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.8.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

view

-0.48

ook

-0.48

 titoli

-0.47

who

-0.47

hdr

-0.47

onerror

-0.46

 storici

-0.46

 sejarah

-0.46

kdo

-0.45

who

-0.45

POSITIVE LOGITS

 فريبيس

1.06

ReusableCell

0.98

 resourceCulture

0.80

PreferredItem

0.79

دانشنامهٔ

0.75

 незавершена

0.71

SharedCtor

0.71

 MainAxisSize

0.71

)"),

0.67

цездатний

0.66

Activations Density 31.845%

tokens used commonly in online forum or user-generated content

apostrophes

No Comments

No Known Activations

tokens used commonly in online forum or user-generated content

apostrophes

No Comments

No Known Activations