INDEX

Explanations

text with references to awards, publication, and achievements

oai_token-act-pair · gemini-2.0-flash

publications

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

__":

-0.55

曖昧さ回避

-0.52

DeleteBehavior

-0.51

^*)

-0.49

LayoutPanel

-0.49

__":

-0.49

WithIOException

-0.49

MessageOf

-0.48

[]:

-0.45

ReusableCell

-0.45

POSITIVE LOGITS

raszamy

0.59

asy

0.58

 peine

0.58

zerű

0.58

InputBorder

0.57

Compensation

0.56

 препратки

0.55

basicConfig

0.54

 Aujourd

0.54

 Compensation

0.53

Activations Density 0.664%

text with references to awards, publication, and achievements

publications

No Comments

No Known Activations