INDEX

Explanations

words and phrases related to competitions, review processes, job applications, education, and optics

oai_token-act-pair · gemini-2.0-flash

round

np_max-act · gemini-2.0-flash

New Auto-Interp

Configuration

google/gemma-scope-2b-pt-transcoders/layer_7/width_16k/average_l0_70

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.7.ln2.hook_normalized

Architecture

jumprelu_transcoder

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Embeds

IFrame

Link

Negative Logits

bootstrapcdn

-1.03

دانشنامهٔ

-0.77

 MainAxisSize

-0.76

SequentialGroup

-0.74



-0.70

Round

-0.68

 Round

-0.67

DockStyle

-0.65

يكب

-0.64

 GenerationType

-0.63

POSITIVE LOGITS

}</

0.47

 natural

0.46

eks

0.45

MONS

0.44

("}\

0.42

 account

0.40

roids

0.40

 report

0.40

 never

0.39

 طبي

0.39

Activations Density 18.034%

words and phrases related to competitions, review processes, job applications, education, and optics

round

No Known Activations