INDEX

Explanations

code snippets and programming language-related text including markup

oai_token-act-pair · gemini-2.0-flash

Portuguese language

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

AndEndTag

-0.60

FILED

-0.51

 Reverso

-0.49

alanta

-0.45

awaiter

-0.44

جوايز

-0.43

En

-0.42

en

-0.42

 snippetHide

-0.42

liferay

-0.41

POSITIVE LOGITS

AddTagHelper

0.68

 surla

0.65

fillType

0.64

 AssemblyCompany

0.62

ParallelGroup

0.62

ReusableCell

0.60

 chrétiens

0.57

Hauptartikel

0.57

makeConstraints

0.57

 createSlice

0.57

Activations Density 0.723%

code snippets and programming language-related text including markup

Portuguese language

No Comments

No Known Activations