INDEX

Explanations

things that are similar/related to each other

oai_token-act-pair · gemini-2.0-flash

as

np_max-act-logits · gemini-2.0-flash

New Auto-Interp

Configuration

google/gemma-scope-2b-pt-transcoders/layer_22/width_16k/average_l0_15

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.22.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

exitRule

-0.62

 vaisselle

-0.54

awaiter

-0.50

stdc

-0.49

 للمعارف

-0.47

ArrowToggle

-0.47

AutoresizingMask

-0.45

 useState

-0.45

 intStringLen

-0.44

رشف

-0.44

POSITIVE LOGITS

]--;

0.73

 &___

0.66

},[])

0.60

μισ

0.60

 Fast

0.60

fast

0.59

edig

0.59

 fast

0.57

 faſt

0.57

gaven

0.56

Activations Density 0.497%

things that are similar/related to each other

as

No Comments

No Known Activations