INDEX

Explanations

words connoting ownership/responsibility, especially related to technology

oai_token-act-pair · gemini-2.0-flash

code or programming terminology

np_token-act-pair-logits · gemini-2.0-flash

is

np_max-act-logits · gemini-2.0-flash

New Auto-Interp

Configuration

google/gemma-scope-2b-pt-transcoders/layer_16/width_16k/average_l0_10

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.16.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

 صوتيه

-0.67

StoreMessageInfo

-0.65

 Monfieur

-0.61

ofition

-0.56

 tartalomajánló

-0.53

colhead

-0.51

 doubtnut

-0.51

iented

-0.50

ouncil

-0.50

 שוליים

-0.50

POSITIVE LOGITS

TagMode

0.65

MigrationBuilder

0.60

AccessFile

0.57

QMetaType

0.53

sizeCache

0.50

sptr

0.50

TemporalType

0.50

FXMLLoader

0.47

τερα

0.47

 autorytatywna

0.47

Activations Density 0.965%

words connoting ownership/responsibility, especially related to technology

code or programming terminology

is

No Comments

No Known Activations