INDEX

Explanations

phrases related to commerce or ordering products.

oai_token-act-pair · gemini-2.0-flash

Hats and watches

np_max-act-logits · gemini-2.0-flash

New Auto-Interp

Configuration

google/gemma-scope-2b-pt-transcoders/layer_25/width_16k/average_l0_41

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.25.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

tagHelperRunner

-0.63

 équipements

-0.58

Климат

-0.58

 InputDecoration

-0.56

uelos

-0.54

UserScript

-0.54

 recevez

-0.53

WebVitals

-0.53

resave

-0.53

rotta

-0.52

POSITIVE LOGITS

 watch

1.16

 Watch

0.95

watch

0.93

Watch

0.89

hat

0.84

脚注の使い方

0.75

pen

0.74

HAT

0.71

bag

0.71

Hat

0.69

Activations Density 8.788%

phrases related to commerce or ordering products.

Hats and watches

No Comments

No Known Activations