INDEX

Explanations

code-related keywords like "len", "list", "def", "string", "uint", "return", etc

oai_token-act-pair · gemini-2.0-flash

len

np_max-act · gemini-2.0-flash

New Auto-Interp

Configuration

google/gemma-scope-2b-pt-transcoders/layer_7/width_16k/average_l0_70

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.7.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

DockStyle

-0.66

+#+#

-0.65

StructEnd

-0.60

UrlResolution

-0.59

PreferredItem

-0.59

XmlAccessType

-0.57

ніципа

-0.57

InSection

-0.56

 HasFactory

-0.55

ंदीखरीदारी

-0.53

POSITIVE LOGITS

HEIM

0.48

NameLabel

0.48

?></

0.47

Naissance

0.47

الحياه

0.46

VisualStudio

0.45

nom

0.45

 Private

0.44

 Erfahrung

0.43

buku

0.43

Activations Density 4.936%

code-related keywords like "len", "list", "def", "string", "uint", "return", etc

len

No Comments

No Known Activations