INDEX

Explanations

uses of the word "take" or discusses math and adversity

oai_token-act-pair · gemini-2.0-flash

take

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

RegressionTest

-0.62

 Extragalactic

-0.60

tingu

-0.58

 jspb

-0.57

ArrowToggle

-0.57

 verticale

-0.57

interopRequire

-0.56

AnchorStyles

-0.55

CreateModel

-0.54

CloseOperation

-0.54

POSITIVE LOGITS

 take

1.23

 takes

1.16

take

1.13

 Take

1.04

Take

1.04

 Takes

1.01

 took

0.98

Takes

0.97

 Taking

0.96

takes

0.96

Activations Density 2.290%

uses of the word "take" or discusses math and adversity

take

No Comments

No Known Activations