INDEX

Explanations

code snippets, variable names, and file paths

oai_token-act-pair · gemini-2.0-flash

code

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

WriteTagHelper

-0.78

MigrationBuilder

-0.72

AddTagHelper

-0.68

featureID

-0.67

Datuak

-0.66

">—

-0.66

IndentedString

-0.65

 EconPapers

-0.60

 commerciaux

-0.56

 насељу

-0.56

POSITIVE LOGITS

ArgumentParser

0.59

UMBIA

0.48

 argc

0.47

 متحده

0.45

icitis

0.44

 Quelles

0.44

icke

0.43

 وتسجيلات

0.43

handelt

0.43

eben

0.42

Activations Density 1.676%

code snippets, variable names, and file paths

code

No Comments

No Known Activations