INDEX

Explanations

words related to political science, natural sciences, and mathematics

oai_token-act-pair · gemini-2.0-flash

complex abstract issues

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

 defaultstate

-0.80

argout

-0.79

saraba

-0.70

AutoField

-0.68

aspectj

-0.62

rungsseite

-0.60

ServletException

-0.59

orsese

-0.59

OCCURRED

-0.59

twimg

-0.59

POSITIVE LOGITS

Aca

0.51

Vtbl

0.51

 Lynx

0.48

waits

0.47

ulously

0.46

NUMX

0.46

sexual

0.45

orgeous

0.45

 vägen

0.44

 neck

0.44

Activations Density 24.339%

words related to political science, natural sciences, and mathematics

complex abstract issues

No Comments

No Known Activations