INDEX

Explanations

words related to accomplishments, achievements, or being happy

oai_token-act-pair · gemini-2.0-flash

concepts

np_max-act · gemini-2.0-flash

New Auto-Interp

Configuration

google/gemma-scope-2b-pt-transcoders/layer_8/width_16k/average_l0_52

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.8.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

AndEndTag

-0.47

 korban

-0.45

(:,:,

-0.45

orgon

-0.44

 wikipagina

-0.44



-0.43

 conclure

-0.43

AlterField

-0.43

{*}

-0.42

ToListAsync

-0.41

POSITIVE LOGITS

__*/

0.64

AsUp

0.63

IndentedString

0.62

TestingModule

0.61

HideFlags

0.58

 "..\..\..\

0.56

 scienti

0.55

IsContent

0.54

NUMX

0.54

 conserved

0.53

Activations Density 35.175%

words related to accomplishments, achievements, or being happy

concepts

No Comments

No Known Activations