INDEX

Explanations

numerical measurements

oai_token-act-pair · gemini-2.0-flash

specifications

np_max-act-logits · gemini-2.0-flash

New Auto-Interp

Configuration

google/gemma-scope-2b-pt-transcoders/layer_20/width_16k/average_l0_11

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.20.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

 water

-0.49

Ag

-0.49

-0.48

 total

-0.47

ss

-0.46

sa

-0.46

cu

-0.46

 word

-0.45

ov

-0.44

POSITIVE LOGITS

 EconPapers

0.76

 NSCoder

0.67

 approximately

0.66

httphttps

0.66

 eighty

0.65

TintMode

0.65

ThroughAttribute

0.65

 sixty

0.65

WebServlet

0.65

 approx

0.63

Activations Density 2.032%

numerical measurements

specifications

No Comments

No Known Activations