INDEX

Explanations

technical scientific writing that reference half-life, time, or deficits

oai_token-act-pair · gemini-2.0-flash

half

np_max-act-logits · gemini-2.0-flash

New Auto-Interp

Configuration

google/gemma-scope-2b-pt-transcoders/layer_24/width_16k/average_l0_37

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.24.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

 half

-2.98

Half

-2.78

 Half

-2.78

half

-2.77

 HALF

-2.56

HALF

-2.30

 halves

-2.17

 halfway

-2.05

 halv

-1.91

 setengah

-1.84

POSITIVE LOGITS

EnableWeb

0.47

PageContext

0.46

Rüyada

0.45

astify

0.40

AutoSize

0.39

usepackage

0.39

dah

0.38

葩

0.38

<%=

0.38

↵

0.37

Activations Density 3.313%

technical scientific writing that reference half-life, time, or deficits

half

No Comments

No Known Activations