INDEX

Explanations

second person pronouns and words associated with relationships

oai_token-act-pair · gemini-2.0-flash

Number two

np_max-act-logits · gemini-2.0-flash

New Auto-Interp

Configuration

google/gemma-scope-2b-pt-transcoders/layer_22/width_16k/average_l0_15

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.22.ln2.hook_normalized

Architecture

jumprelu_transcoder

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Embeds

IFrame

Link

Negative Logits

\{\\

-0.54

-0.48

asiun

-0.46

tvguidetime

-0.44

tifact

-0.44

NOPQRST

-0.43

Przypisy

-0.43

первых

-0.42

ServletConfig

-0.42

참고

-0.42

POSITIVE LOGITS

two

3.14

two

2.73

 deux

2.50

Two

2.38

Two

2.22

TWO

2.13

 zwei

2.11

 dois

2.08

TWO

2.02

 duas

1.95

Activations Density 2.401%

second person pronouns and words associated with relationships

Number two

No Known Activations