INDEX

Explanations

second-person pronouns and possessives like "you" and "your"

oai_token-act-pair · gemini-2.0-flash

your

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

########.

-0.77

 AssemblyVersion

-0.67

 your

-0.65

your

-0.65

Your

-0.63

 Your

-0.58

 vostre

-0.58

 podes

-0.57

BeginContext

-0.56

 dumne

-0.56

POSITIVE LOGITS

 preferred

0.60

Efq

0.60

 favorite

0.58

 choice

0.55

 worst

0.54

 specific

0.52

 favourite

0.52

ropriate

0.52

 chosen

0.52

own

0.52

Activations Density 4.227%

second-person pronouns and possessives like "you" and "your"

your

No Comments

No Known Activations