INDEX

Explanations

code snippets, especially related to databases

oai_token-act-pair · gemini-2.0-flash

Data Fields

np_max-act-logits · gemini-2.0-flash

New Auto-Interp

Configuration

google/gemma-scope-2b-pt-transcoders/layer_19/width_16k/average_l0_12

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.19.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

 betweenstory

-0.81

 '\\;'

-0.80

CodeAttribute

-0.80

LEGGI

-0.79

 <=",

-0.75

 Wikiseite

-0.73

انيف

-0.72

 sumpay

-0.71

TargetException

-0.71

contentLoaded

-0.71

POSITIVE LOGITS

 price

0.62

 date

0.61

 subject

0.60

 status

0.60

 Number

0.58

 number

0.57

Number

0.57

 trình

0.56

status

0.56

Status

0.56

Activations Density 11.709%

code snippets, especially related to databases

Data Fields

No Comments

No Known Activations