INDEX

Explanations

source code

oai_token-act-pair · gemini-2.0-flash

code

np_max-act-logits · gemini-2.0-flash

New Auto-Interp

Configuration

google/gemma-scope-2b-pt-transcoders/layer_24/width_16k/average_l0_37

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.24.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

-0.46

<eos>

-0.43

“

-0.42

↵↵

-0.40

-0.34

-0.33

«

-0.32

-0.31

-0.30

POSITIVE LOGITS

Efq

1.45

 Monfieur

1.25

 Majefty

1.19

GEBURTSDATUM

1.18

 Jefus

1.15

 avoient

1.10

 myſelf

1.09

 ―――――

1.07

 Diſ

1.07

ſelf

1.07

Activations Density 21.961%

source code

code

No Comments

No Known Activations