INDEX

Explanations

code snippets and discussion of code, like from StackOverflow

oai_token-act-pair · gemini-2.0-flash

Programming solutions

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

CloseOperation

-0.99

AndEndTag

-0.97

tagHelperRunner

-0.95

">//

-0.93

LookAnd

-0.89

findpost

-0.81

 BoxFit

-0.80

 تانيه

-0.78

 مرئيه

-0.78

ftagPool

-0.75

POSITIVE LOGITS

0.50

↵↵

0.46

 inside

0.44

0.41

↵

0.41

 where

0.41

for

0.40

 today

0.40

Activations Density 10.318%

code snippets and discussion of code, like from StackOverflow

Programming solutions

No Comments

No Known Activations