INDEX

Explanations

mathematical or physics papers or publications or related terms like Phys, Rev, arXiv, hep, th, and Nucl

oai_token-act-pair · gemini-2.0-flash

Research papers

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

Not in Any Lists

No Comments

Negative Logits

^(@)

-0.92

Efq

-0.85

 resourceCulture

-0.84

NUMX

-0.83

>\<^

-0.80

extAlignment

-0.80

 Monfieur

-0.79

 uſed

-0.78

 myſelf

-0.78

IntoConstraints

-0.75

POSITIVE LOGITS

0.57

ißt

0.48

__*/

0.48

0.47

port

0.47

0.46

0.44

le

0.43

ies

0.43

Activations Density 12.177%

mathematical or physics papers or publications or related terms like Phys, Rev, arXiv, hep, th, and Nucl

Research papers

No Comments

No Known Activations