INDEX

Explanations

code documentation blocks

oai_token-act-pair · gemini-2.0-flash

*/

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

twimg

-0.73

ConstraintMaker

-0.72

rungsseite

-0.71

ISupport

-0.71

WriteBarrier

-0.67

 cherchés

-0.66

webElementXpaths

-0.64

 للاسماء

-0.63

asiun

-0.63

Enllaces

-0.63

POSITIVE LOGITS

↵

0.56

ificantly

0.49

licação

0.44

 exemplu

0.41

umatic

0.40

yorsunuz

0.39

 specchio

0.39

őség

0.39

<bos>

0.39

 manu

0.39

Activations Density 0.384%

code documentation blocks

*/

No Comments

No Known Activations