INDEX

Explanations

words and phrases related to experimental methodology in scientific papers.

oai_token-act-pair · gemini-2.0-flash

reference

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

 ModelExpression

-0.92

 Италијани

-0.90

 ―――――

-0.87

 Monfieur

-0.87

protoimpl

-0.83

 Roskov

-0.83

 autorytatywna

-0.81

 ddelweddau

-0.79

 <>",

-0.79

PerformLayout

-0.79

POSITIVE LOGITS

 reference

1.52

 Reference

1.27

reference

1.16

Reference

1.12

 REFERENCE

1.10

 refer

1.07

ref

1.02

REFERENCE

0.96

 referencia

0.94

 riferimento

0.93

Activations Density 3.166%

words and phrases related to experimental methodology in scientific papers.

reference

No Comments

No Known Activations