INDEX

Explanations

words/phrases expressing enjoyment or appreciation

oai_token-act-pair · gemini-2.0-flash

Positive sentiment

np_max-act · gemini-2.0-flash

New Auto-Interp

Configuration

google/gemma-scope-2b-pt-transcoders/layer_4/width_16k/average_l0_88

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.4.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

abetes

-0.94

WebVitals

-0.89

findpost

-0.82

UnsafeEnabled

-0.80

Personendaten

-0.77

awtextra

-0.77

ագրություններ

-0.76

GIVEREF

-0.76

 AppColors

-0.75

RenderAtEndOf

-0.75

POSITIVE LOGITS

reta

0.49

 amazing

0.49

0.44

0.43

Regional

0.42

so

0.40

Mar

0.40

as

0.40

 regional

0.40

 under

0.39

Activations Density 2.569%

words/phrases expressing enjoyment or appreciation

Positive sentiment

No Comments

No Known Activations