INDEX

Explanations

java code

oai_token-act-pair · gemini-2.0-flash

Code snippets

np_max-act-logits · gemini-2.0-flash

New Auto-Interp

Configuration

google/gemma-scope-2b-pt-transcoders/layer_25/width_16k/average_l0_41

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.25.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

putInt

-0.63

idity

-0.62

Spoljašnje

-0.61

 IndexError

-0.61

 kaarangay

-0.59

 aikaa

-0.58

AND

-0.58

 honneur

-0.56

 doigt

-0.56

iconque

-0.56

POSITIVE LOGITS

ImageContext

0.63

UIControlState

0.56

awtextra

0.50

the

0.49

tvguidetime

0.49

ieteur

0.48

 onPostExecute

0.46

DockStyle

0.44

indd

0.43

orianCalendar

0.42

Activations Density 12.295%

java code

Code snippets

No Comments

No Known Activations