INDEX

Explanations

a wide variety of terms related to specific people, places, things, and organizations

oai_token-act-pair · gemini-2.0-flash

international affairs

np_max-act · gemini-2.0-flash

New Auto-Interp

Configuration

google/gemma-scope-2b-pt-transcoders/layer_8/width_16k/average_l0_52

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.8.ln2.hook_normalized

Architecture

jumprelu_transcoder

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 AppColors

-0.85

]")]

-0.75

OrNil

-0.69

 Paglinawan

-0.67

OGND

-0.65

TagMode

-0.65

Étymologie

-0.65

 CreateTagHelper

-0.65

 Offisielt

-0.65

$.

-0.64

POSITIVE LOGITS

Inc

0.68

inc

0.60

 Incorporated

0.51

INC

0.49

Jr

0.48

под

0.48

mybatisplus

0.48

unc

0.47

 GmbH

0.46

 Curry

0.45

Activations Density 7.564%

a wide variety of terms related to specific people, places, things, and organizations

international affairs

No Comments

No Known Activations