INDEX

Explanations

words related to helping professions, medical treatment, being the subject of charity, and hostages.

oai_token-act-pair · gemini-2.0-flash

ben

np_max-act · gemini-2.0-flash

New Auto-Interp

Configuration

google/gemma-scope-2b-pt-transcoders/layer_7/width_16k/average_l0_70

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.7.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

MENAFN

-0.60



-0.53

semantics

-0.48

Bande

-0.48

 Xunit

-0.48

 tweet

-0.47

έσ

-0.46

 metav

-0.45

 Geological

-0.44

发表于

-0.44

POSITIVE LOGITS

SourceChecksum

0.85

StructEnd

0.75

contentLoaded

0.68

WriteTagHelper

0.67

 sonno

0.61

RenderAtEndOf

0.59

elemField

0.59

TagMode

0.57

neté

0.55

ignty

0.55

Activations Density 5.518%

words related to helping professions, medical treatment, being the subject of charity, and hostages.

ben

No Comments

No Known Activations