INDEX

Explanations

question prompts soliciting a response

oai_token-act-pair · gemini-2.0-flash

Question-answer/uncertainty

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

 through

-0.39

紹

-0.39

 Zwar

-0.38

ц

-0.38

 minst

-0.37

blico

-0.37

vka

-0.36

arial

-0.36

 camb

-0.36

atively

-0.36

POSITIVE LOGITS

StoryboardSegue

1.03

UserScript

1.02

IntoConstraints

0.97

findpost

0.95

 disambiguazione

0.91

 useAppContext

0.91

 Chwiliwch

0.90

 snippetHide

0.88

 CreateTagHelper

0.88

Tikang

0.88

Activations Density 0.115%

question prompts soliciting a response

Question-answer/uncertainty

No Comments

No Known Activations