INDEX

Explanations

code snippets, especially related to javascript and html

oai_token-act-pair · gemini-2.0-flash

Plural nouns

np_max-act-logits · gemini-2.0-flash

New Auto-Interp

Configuration

google/gemma-scope-2b-pt-transcoders/layer_24/width_16k/average_l0_37

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.24.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

Efq

-0.63

StructEnd

-0.62

NewUrlParser

-0.59

 الرياضيه

-0.57

 समीक्षक

-0.57

Eſ

-0.56

$_"

-0.56

 ویکی‌پدی

-0.52

NUMX

-0.52

 ModelExpression

-0.51

POSITIVE LOGITS

 Trains

0.83

 Companies

0.80

 Reports

0.78

 Tracks

0.78

 Images

0.77

 Films

0.77

 Requests

0.76

 Orders

0.76

 Posts

0.76

 Plots

0.75

Activations Density 32.229%

code snippets, especially related to javascript and html

Plural nouns

No Comments

No Known Activations