INDEX

Explanations

negative numbers

oai_token-act-pair · gemini-2.0-flash

math equations and numbers

np_max-act-logits · gemini-2.0-flash

New Auto-Interp

Configuration

google/gemma-scope-2b-pt-transcoders/layer_20/width_16k/average_l0_11

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.20.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

AutoField

-0.58

 fourth

-0.58

 Fourteenth

-0.56

 keempat

-0.56

-0.54

ölker

-0.53

 Fourteen

-0.53

十四

-0.52

økt

-0.50

 Edelstahl

-0.50

POSITIVE LOGITS

ParallelGroup

0.59

 ostavi

0.57

 GenerationType

0.53

يديا

0.53

 FetchType

0.49

 skri

0.49

 resourceCulture

0.49

 sportback

0.49

 Seven

0.49

UserScript

0.49

Activations Density 1.087%

negative numbers

math equations and numbers

No Comments

No Known Activations