INDEX

Explanations

the word 'blue'

oai_token-act-pair · gemini-2.0-flash

Blue

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

ScopeManager

-0.84

DockStyle

-0.79

httphttps

-0.73

 CURIAM

-0.71

TagMode

-0.67

ImageContext

-0.67

 quæ

-0.64

 göre

-0.61

 beholder

-0.57

upol

-0.57

POSITIVE LOGITS

#![

0.54

hern

0.49

Rib

0.47

gette

0.46

λης

0.46

Bioaccumulative

0.46

 hair

0.45

[['

0.45

INCT

0.45

 التالي

0.45

Activations Density 0.395%

the word 'blue'

Blue

No Comments

No Known Activations