INDEX

Explanations

the word "professional", and sometimes words associated with it.

oai_token-act-pair · gemini-2.0-flash

professional

np_max-act · gemini-2.0-flash

New Auto-Interp

Configuration

google/gemma-scope-2b-pt-transcoders/layer_4/width_16k/average_l0_88

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.4.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

 professional

-2.38

Professional

-2.25

professional

-2.17

 Professional

-2.11

 PROFESSIONAL

-1.94

 profesional

-1.80

PROFESSIONAL

-1.71

 profissional

-1.64

 professionally

-1.58

 professionelle

-1.55

POSITIVE LOGITS

demic

0.59

참고

0.58

pecia

0.53

Personendaten

0.52

 fuoco

0.51

bolts

0.50

ilets

0.49

 fogo

0.49

Begriffsklä

0.49

 phụ

0.49

Activations Density 2.739%

the word "professional", and sometimes words associated with it.

professional

No Comments

No Known Activations