INDEX

Explanations

words describing processes like applying a coating, manufacturing, providing nourishment, or physical change

oai_token-act-pair · gemini-2.0-flash

Providing something

np_max-act · gemini-2.0-flash

New Auto-Interp

Configuration

google/gemma-scope-2b-pt-transcoders/layer_0/width_16k/average_l0_76

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.0.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

 ploughing

-1.25

 plowing

-1.17

 voting

-1.16

 cooking

-1.14

voting

-1.07

 feeding

-1.05

 shooting

-1.05

 printing

-1.04

 scanning

-1.04

 booking

-1.02

POSITIVE LOGITS

ING

0.93

ting

0.90

ing

0.88

izing

0.81

ging

0.80

 Using

0.79

ding

0.77

Using

0.73

ating

0.73

ying

0.73

Activations Density 4.332%

words describing processes like applying a coating, manufacturing, providing nourishment, or physical change

Providing something

No Comments

No Known Activations