INDEX

Explanations

code snippets, especially in languages like Java, Python, and Javascript.

oai_token-act-pair · gemini-2.0-flash

right parenthesis

np_max-act · gemini-2.0-flash

New Auto-Interp

Configuration

google/gemma-scope-2b-pt-transcoders/layer_8/width_16k/average_l0_52

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.8.ln2.hook_normalized

Architecture

jumprelu_transcoder

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

FailureListener

-0.66

XmlEnum

-0.57

:✨

-0.55

клопе

-0.54

ViewFeatures

-0.53

 المعيارى

-0.52

 AssemblyCulture

-0.48

 event

-0.48

EDEFAULT

-0.48

 protoimpl

-0.46

POSITIVE LOGITS

IComponent

0.54

})();

0.53

 autorytatywna

0.53

 reluctance

0.53

ASR

0.52

 Nautilus

0.52

 IndexPath

0.51

 resistance

0.51

}}">

0.50

 Chrif

0.50

Activations Density 22.188%

code snippets, especially in languages like Java, Python, and Javascript.

right parenthesis

No Comments

No Known Activations