INDEX

Explanations

code documentation blocks in a programming language

oai_token-act-pair · gemini-2.0-flash

*/

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

 виправивши

-1.02

 kasarigan

-0.98

GOTREF

-0.91

parsedMessage

-0.91

.*")]

-0.89

__(/*!

-0.89

+");

-0.88

CloseOperation

-0.87

 >=",

-0.87

"]).

-0.85

POSITIVE LOGITS

0.44

0.43

↵

0.42

↵↵

0.41

0.40

0.38

ta

0.38

0.36

Activations Density 4.822%

code documentation blocks in a programming language

*/

No Comments

No Known Activations