INDEX

Explanations

words, letters and punctuation that frequently appear together and are not typically meaningful on their own.

oai_token-act-pair · 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

GEBURTS

-0.85

 AssemblyCompany

-0.72

 виправивши

-0.65

XmlAccessorType

-0.63

NUMX

-0.62

ViewImports

-0.61

righted

-0.60

IsContent

-0.60

DebuggerStep

-0.59

Còn

-0.59

POSITIVE LOGITS

Captor

0.46

ágos

0.44

رد

0.44

weta

0.43

矩

0.43

kammer

0.43

odb

0.42

Autoritní

0.42

Vidite

0.41

รับ

0.40

Activations Density 44.711%

words, letters and punctuation that frequently appear together and are not typically meaningful on their own.

No Comments

No Known Activations