INDEX

Explanations

a jumble of words involving contracts, ownership, motivation and processes.

oai_token-act-pair · gemini-2.0-flash

Possessive pronouns

np_max-act-logits · gemini-2.0-flash

New Auto-Interp

Configuration

google/gemma-scope-2b-pt-transcoders/layer_20/width_16k/average_l0_11

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.20.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

parsedMessage

-1.05

^(@)

-0.98

CloseOperation

-0.98

LookAnd

-0.96

DockStyle

-0.95

windowFixed

-0.89

 itſelf

-0.87

 onCreateView

-0.87

AddTagHelper

-0.86

WithIOException

-0.85

POSITIVE LOGITS

 своих

1.49

his

1.42

 seus

1.39

seu

1.37

 their

1.35

 своей

1.31

 свою

1.30

 свої

1.30

 своего

1.30

 své

1.29

Activations Density 4.841%

a jumble of words involving contracts, ownership, motivation and processes.

Possessive pronouns

No Comments

No Known Activations