INDEX

Explanations

locations in Brisbane

oai_token-act-pair · gemini-2.0-flash

Foreign language/code

np_max-act-logits · gemini-2.0-flash

New Auto-Interp

Configuration

google/gemma-scope-2b-pt-transcoders/layer_23/width_16k/average_l0_25

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.23.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

AndFlush

-0.42

DEVICES

-0.41

 Rubin

-0.37

 wafer

-0.37

ляться

-0.37

 voce

-0.36

 professionale

-0.36

sbereich

-0.35

 fire

-0.35

 fires

-0.35

POSITIVE LOGITS

脚注の使い方

0.78

 Monfieur

0.75

ſelves

0.74

WriteTagHelper

0.72

帖最后由

0.69

 Theſe

0.68

 myſelf

0.66

 Độ

0.64

bootstrapcdn

0.63

 >=",

0.63

Activations Density 0.621%

locations in Brisbane

Foreign language/code

No Comments

No Known Activations