INDEX

Explanations

first and second person pronouns

oai_token-act-pair · gemini-2.0-flash

We/I

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

msgTypes

-0.54

 createSprite

-0.53

----</

-0.51

出版年

-0.51

psin

-0.49

 Wicidata

-0.49

WireFormatLite

-0.49

().__

-0.48

insp

-0.48

 dire

-0.48

POSITIVE LOGITS

 AssemblyCulture

0.53

GRAFIA

0.50

 Inseln

0.50

 compartida

0.49

droje

0.49

 économies

0.49

AndroidJUnit

0.48

$_"

0.48

niosek

0.47

 suprême

0.47

Activations Density 2.032%

first and second person pronouns

We/I

No Comments

No Known Activations