INDEX

Explanations

code snippets with high or low number

oai_token-act-pair · gemini-2.0-flash

Code and URLs

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

 Nine

-0.64

 Eight

-0.60

تمبر

-0.59

GenerationType

-0.58

 esternos

-0.56

WebElementEntity

-0.55

 oito

-0.54

 eight

-0.53

POSITIVE LOGITS

0.60

0.57

 Lightboxes

0.56

***************/

0.56

fif

0.54

alz

0.53

 Fifty

0.53

هذه

0.52

makeText

0.51

熨

0.51

Activations Density 0.332%

code snippets with high or low number

Code and URLs

No Comments

No Known Activations