INDEX

Explanations

words and phrases related to research, medicine and resolving problems

oai_token-act-pair · gemini-2.0-flash

problems

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

Aiheesta

-0.59

Diweddarwch

-0.50

itemBuilder

-0.50

таратура

-0.48

enterOuterAlt

-0.48

oplasts

-0.48

Література

-0.47

itals

-0.47

SUCCEEDED

-0.46

 expressive

-0.46

POSITIVE LOGITS

 problems

1.31

any

1.18

 Problems

1.16

 problem

1.10

problems

1.09

Problems

1.09

Any

1.08

 disputes

1.05

 issues

1.04

Any

1.04

Activations Density 2.235%

words and phrases related to research, medicine and resolving problems

problems

No Comments

No Known Activations