INDEX

Explanations

references to universities and presses

oai_token-act-pair · gemini-2.0-flash

Academic publications

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

-0.83

-0.78

ｐ

-0.75

pn

-0.73

𝑝

-0.69

pn

-0.69

pe

-0.69

pp

-0.68

plist

-0.68

ptest

-0.66

POSITIVE LOGITS

PyExc

0.49

 Post

0.47

Pro

0.44

 Parts

0.44

 Property

0.44

 Part

0.44

Payload

0.43

ритори

0.43

 Paper

0.43

 Press

0.42

Activations Density 0.320%

references to universities and presses

Academic publications

No Comments

No Known Activations