INDEX

Explanations

common phrases like "United States of" and also some category titles.

oai_token-act-pair · gemini-2.0-flash

the

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

USA

-0.93

USA

-0.93

US

-0.90

-0.88

US

-0.82

 United

-0.75

UK

-0.72

usa

-0.72

 UNITED

-0.71

United

-0.70

POSITIVE LOGITS

the

1.13

цездатний

0.69

the

0.68

aux

0.66

kuuta

0.57

MigrationBuilder

0.55

oski

0.54

AddTagHelper

0.54

 sabbia

0.53

Lieu

0.52

Activations Density 1.330%

common phrases like "United States of" and also some category titles.

the

No Comments

No Known Activations