INDEX

Explanations

different forms of the word "global."

oai_token-act-pair · gemini-2.0-flash

global

np_max-act-logits · gemini-2.0-flash

New Auto-Interp

Configuration

google/gemma-scope-2b-pt-transcoders/layer_19/width_16k/average_l0_12

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.19.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

AndEndTag

-0.80

########.

-0.70

 AssemblyCulture

-0.70

 Италијани

-0.70

exitRule

-0.70

thâu

-0.69

 HasFactory

-0.68

UserScript

-0.67

protoimpl

-0.67

HasKey

-0.65

POSITIVE LOGITS

 للمعارف

0.57

enseignements

0.44

程

0.41

 laut

0.40

mujeres

0.40

 segü

0.40

 jornada

0.40

 manches

0.38

 lindos

0.38

 jueces

0.37

Activations Density 0.127%

different forms of the word "global."

global

No Comments

No Known Activations