INDEX

Explanations

code snippets and service related terms

oai_token-act-pair · gemini-2.0-flash

business or web 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

ocyan

-0.52

+#+#

-0.51

phys

-0.49

 thấm

-0.47

 Lexikon

-0.47

 fisik

-0.45

Nor

-0.44

 viejas

-0.44

 sustancias

-0.44

 layak

-0.44

POSITIVE LOGITS

 itſelf

0.85

UnusedPrivate

0.73

ViewImports

0.72

 Spisak

0.67

CopyWith

0.66

".

0.66

Viitteet

0.66

zzleHttp

0.65

 nahilalakip

0.63

matchCondition

0.63

Activations Density 4.113%

code snippets and service related terms

business or web code

No Comments

No Known Activations