INDEX

Explanations

text where first person pronouns are in use

oai_token-act-pair · gemini-2.0-flash

express opinions

np_max-act-logits · gemini-2.0-flash

New Auto-Interp

Configuration

google/gemma-scope-2b-pt-transcoders/layer_19/width_16k/average_l0_12

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.19.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

########.

-0.93

expandindo

-0.52

ChildScrollView

-0.50

 فريبيس

-0.50

AutoScaleMode

-0.50

WebServlet

-0.47

 }}"></

-0.46

 ModelExpression

-0.45

 AssemblyTitle

-0.45

eclared

-0.45

POSITIVE LOGITS

 opinion

1.42

 believe

1.34

 believes

1.27

 belief

1.23

opinion

1.19

 think

1.19

believe

1.19

 thinks

1.17

 believed

1.12

belie

1.12

Activations Density 4.387%

text where first person pronouns are in use

express opinions

No Comments

No Known Activations