INDEX

Explanations

terms related to business, industry, and technology

oai_token-act-pair · gemini-2.0-flash

Companies

np_max-act-logits · gemini-2.0-flash

New Auto-Interp

Configuration

google/gemma-scope-2b-pt-transcoders/layer_25/width_16k/average_l0_41

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.25.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

Fns

-0.62

SPECIFIED

-0.59

nasel

-0.52

piram

-0.51

jutan

-0.50

PreferredItem

-0.50

Cursors

-0.49

FieldBuilder

-0.49

RegressionTest

-0.49

IEFS

-0.48

POSITIVE LOGITS

NDE

0.56

Παραπομπές

0.54

SVN

0.53

 armies

0.52

haustible

0.51

 consuls

0.50

AllAfrica

0.50

 concern

0.50

hdashline

0.49

 téléphonique

0.48

Activations Density 7.186%

terms related to business, industry, and technology

Companies

No Comments

No Known Activations