INDEX

Explanations

sentences that use the word "we", "us", or "our."

oai_token-act-pair · gemini-2.0-flash

we

np_max-act-logits · gemini-2.0-flash

New Auto-Interp

Configuration

google/gemma-scope-2b-pt-transcoders/layer_19/width_16k/average_l0_12

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.19.ln2.hook_normalized

Architecture

jumprelu_transcoder

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

tagHelperRunner

-0.86

вгений

-0.84

Eſ

-0.79

EndInit

-0.77

 فريبيس

-0.77

CloseOperation

-0.76

\{\\

-0.75

 članak

-0.74

 للاسماء

-0.73

 متعلقه

-0.73

POSITIVE LOGITS

0.79

’

0.75

 have

0.73

don

0.68

 should

0.67

can

0.59

 started

0.58

are

0.58

 will

0.57

had

0.56

Activations Density 4.220%

sentences that use the word "we", "us", or "our."

we

No Comments

No Known Activations