INDEX

Explanations

the programming keyword "int" and the variable "i" used in loops

oai_token-act-pair · gemini-2.0-flash

int

np_max-act · gemini-2.0-flash

New Auto-Interp

Configuration

google/gemma-scope-2b-pt-transcoders/layer_12/width_16k/average_l0_6

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.12.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

SuccessListener

-0.63

-0.59

complexContent

-0.59

úgó

-0.57

altezza

-0.57

ValueStyle

-0.56

galus

-0.55

 JpaRepository

-0.54

ennis

-0.53

ètre

-0.52

POSITIVE LOGITS

principalColumn

0.79

 protoimpl

0.57

TagHelper

0.57

abilia

0.57

onActivityResult

0.54

 gyhoeddwyd

0.51

skjaer

0.48

BrowserModule

0.48

 AssemblyCompany

0.46

 liable

0.45

Activations Density 0.113%

the programming keyword "int" and the variable "i" used in loops

int

No Comments

No Known Activations