INDEX

Explanations

java code

oai_token-act-pair · gemini-2.0-flash

Code

np_max-act-logits · gemini-2.0-flash

New Auto-Interp

Configuration

google/gemma-scope-2b-pt-transcoders/layer_19/width_16k/average_l0_12

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.19.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

SOUNDBITE

-0.49

TagMode

-0.45

IndentedString

-0.44

kæ

-0.43

 szcze

-0.43

échelle

-0.42

 mode

-0.42

onView

-0.41

UnusedPrivate

-0.41

new

-0.41

POSITIVE LOGITS

+#+#

0.76

CppCodeGen

0.66

RTEX

0.63

 deport

0.63

putra

0.61

AddTagHelper

0.60

 Pingback

0.60

 opal

0.60

 ffilmiau

0.59

 onBind

0.59

Activations Density 2.022%

java code

Code

No Comments

No Known Activations