INDEX

Explanations

phrases related to confusion when expressing an idea

oai_token-act-pair · gemini-2.0-flash

Indicates something is wrong

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

 vrai

-0.51

true

-0.50

 survived

-0.48

 enkelt

-0.48

 untouched

-0.47

TagHelper

-0.46

 verdadero

-0.46

 onResponse

-0.45

atric

-0.45

 adev

-0.45

POSITIVE LOGITS



0.68

 inconvenient

0.64

 invokingState

0.62

Lähteet

0.61

 irregular

0.61

Bad

0.61

 dubious

0.60

ContentAsync

0.59

Bad

0.57

 invalid

0.57

Activations Density 2.219%

phrases related to confusion when expressing an idea

Indicates something is wrong

No Comments

No Known Activations