INDEX

Explanations

the words "kind" or "sort."

oai_token-act-pair · gemini-2.0-flash

sort kind

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 itſelf

-1.30

ſelf

-1.28

 myſelf

-1.26

InjectAttribute

-1.25

 تانيه

-1.25

 שוליים

-1.23

ArgsConstructor

-1.22

ſelves

-1.20

 ―――――

-1.19

 ſtate

-1.17

POSITIVE LOGITS

0.90

<eos>

0.82

0.80

↵↵

0.79

↵

0.77

0.76

0.72

0.71

0.68

Activations Density 0.548%

the words "kind" or "sort."

sort kind

No Comments

No Known Activations