INDEX

Explanations

first person pronouns and contractions

oai_token-act-pair · gemini-2.0-flash

I/you

np_max-act-logits · gemini-2.0-flash

New Auto-Interp

Configuration

google/gemma-scope-2b-pt-transcoders/layer_25/width_16k/average_l0_41

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.25.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

 have

-1.01

have

-0.96

Have

-0.95

 Have

-0.91

has

-0.74

Has

-0.74

has

-0.74

HAVE

-0.69

 HAVE

-0.67

 telah

-0.66

POSITIVE LOGITS



0.73

 '\\;'

0.61

 StatefulWidget

0.58

 <>",

0.58

ANTLR

0.58

Personensuche

0.57

 kasarigan

0.57

DockStyle

0.56

PreferredItem

0.56

Gambas

0.55

Activations Density 4.961%

first person pronouns and contractions

I/you

No Comments

No Known Activations