INDEX

Explanations

code-related terms such as arrays and DataFrames

oai_token-act-pair · gemini-2.0-flash

Code, programming

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

┫

-0.44

 protoimpl

-0.44

 modern

-0.44

waitKey

-0.43

 block

-0.43

AccessorTable

-0.43

 Song

-0.41

liyor

-0.41

("\

-0.40

tokenize

-0.40

POSITIVE LOGITS

ValueStyle

0.88

 MessageBoxIcon

0.75

脚注の使い方

0.73

UseVisualStyle

0.72

 AssemblyCulture

0.68

bootstrapcdn

0.66

SequentialGroup

0.64

出版年

0.64

 sumpay

0.63

 المعيارى

0.61

Activations Density 1.758%

code-related terms such as arrays and DataFrames

Code, programming

No Comments

No Known Activations