INDEX

Explanations

phrases where people are offering advice to others

oai_token-act-pair · gemini-2.0-flash

You

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

 YOUR

-0.83

YOUR

-0.81

your

-0.80

 your

-0.79

Your

-0.75

yours

-0.74

 Your

-0.74

YOU

-0.74

 yourself

-0.73

 yours

-0.70

POSITIVE LOGITS

 mentioned

0.59

 described

0.59

 listed

0.54

 erwähnt

0.52

 quoted

0.51

 apparently

0.50

 quên

0.50

 spoke

0.50

 mention

0.50

/******/

0.49

Activations Density 0.681%

phrases where people are offering advice to others

You

No Comments

No Known Activations