INDEX

Explanations

words related to collaboration, organizations, and data analysis.

oai_token-act-pair · gemini-2.0-flash

other

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

 بتاريخ

-0.63

 виправивши

-0.59

 propOrder

-0.56

CONCURRENT

-0.53

orsal

-0.52

﴾

-0.52

 kader

-0.50

PreferredItem

-0.50

MigrationBuilder

-0.50

prehen

-0.49

POSITIVE LOGITS

ISupport

0.68

 myſelf

0.59

 Monfieur

0.58

 houſe

0.58

 greateſt

0.57

Efq

0.57

 Majefty

0.56

شهاد

0.55

 ModelExpression

0.54

 שוליים

0.53

Activations Density 1.764%

words related to collaboration, organizations, and data analysis.

other

No Comments

No Known Activations