INDEX

Explanations

references to national institutes and similar organizations

oai_token-act-pair · gemini-2.0-flash

institutes and organizations

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

 INSEE

-0.44

TagHelper

-0.42

 flesta

-0.40

 Zwar

-0.39

openSession

-0.38

 mercredi

-0.36

 burden

-0.36

setN

-0.35

 devrez

-0.35

 despacho

-0.35

POSITIVE LOGITS

+#+

0.77

dafx

0.75

WriteTagHelper

0.74

 Normdatei

0.70

 ddelweddau

0.68

MigrationBuilder

0.68

 الدولى

0.65

ArrowToggle

0.63

 transfieras

0.63

انيف

0.63

Activations Density 0.872%

references to national institutes and similar organizations

institutes and organizations

No Comments

No Known Activations