INDEX

Explanations

mentions of death or dying alongside related concepts like violence or marriage

oai_token-act-pair · gemini-2.0-flash

die

np_max-act-logits · gemini-2.0-flash

New Auto-Interp

Configuration

google/gemma-scope-2b-pt-transcoders/layer_20/width_16k/average_l0_11

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.20.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

AddTagHelper

-1.06

RenderAtEndOf

-1.05

ThroughAttribute

-0.98

tagHelperRunner

-0.98

 '\\;'

-0.94

 otomatig

-0.90

 للاسماء

-0.87

ArrowToggle

-0.87

InjectAttribute

-0.86

存于互联网档案馆

-0.84

POSITIVE LOGITS

by

0.56

due

0.52

 from

0.50

 about

0.44

0.41

of

0.40

jú

0.39

hawatir

0.38

uni

0.36

out

0.36

Activations Density 0.607%

mentions of death or dying alongside related concepts like violence or marriage

die

No Comments

No Known Activations