INDEX

Explanations

code snippets, particularly related to Android layouts, with attributes like "id", "layout", "text", "color" and "textSize"

oai_token-act-pair · gemini-2.0-flash

Code and filenames

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

 myſelf

-1.06

AndEndTag

-1.04

 '\\;'

-0.98

UserScript

-0.98

 дописавши

-0.95

EndInit

-0.92

OGND

-0.91

LookAnd

-0.91

 StringTokenizer

-0.90

__*/

-0.90

POSITIVE LOGITS

nah

0.41

far

0.41

 posi

0.39

no

0.39

get

0.39

lin

0.38

ed

0.38

 силу

0.38

sula

0.38

 positive

0.38

Activations Density 1.233%

code snippets, particularly related to Android layouts, with attributes like "id", "layout", "text", "color" and "textSize"

Code and filenames

No Comments

No Known Activations