INDEX

Explanations

This neuron detects a variety of syntax that is common in various coding languages, such as HTML, C++, Python, and others, as well as some chemical names

oai_token-act-pair · gemini-2.0-flash

computer code

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

脚注の使い方

-0.78

IntoConstraints

-0.71

ksessa

-0.70

SuspendLayout

-0.68

 فريبيس

-0.67

spaceBetween

-0.65

protoimpl

-0.64

 CreateTagHelper

-0.64

BufferException

-0.63

 EClass

-0.63

POSITIVE LOGITS

"><?

0.40

">${

0.36

astéro

0.35

 cliquant

0.34

kmale

0.32

 developers

0.32

 Paterson

0.31

BatchNorm

0.31

envolvimento

0.31

 trụ

0.31

Activations Density 0.402%

This neuron detects a variety of syntax that is common in various coding languages, such as HTML, C++, Python, and others, as well as some chemical names

computer code

No Comments

No Known Activations

This neuron detects a variety of syntax that is common in various coding languages, such as HTML, C++, Python, and others, as well as some chemical names

computer code

No Comments

No Known Activations