INDEX

Explanations

the word "term" followed by words that indicate duration

oai_token-act-pair · gemini-2.0-flash

term

np_max-act · gemini-2.0-flash

New Auto-Interp

Configuration

google/gemma-scope-2b-pt-transcoders/layer_0/width_16k/average_l0_76

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.0.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

पया

-0.77

VersionUID

-0.65

存于互联网档案馆

-0.59

 AssemblyProduct

-0.53

 AssemblyCulture

-0.52

 algorit

-0.52

Skocz

-0.52

 Matta

-0.52

zaamheid

-0.52

 voting

-0.51

POSITIVE LOGITS

 kautta

0.66

<bos>

0.64

 kuin

0.62

erapeu

0.61

 BitmapFactory

0.60

enziali

0.59

 avulla

0.58

ptonshire

0.58

 mukana

0.57

 bekas

0.56

Activations Density 1.084%

the word "term" followed by words that indicate duration

term

No Comments

No Known Activations