INDEX

Explanations

conditions in code, specifically comparisons where a value is greater than zero

oai_token-act-pair · gemini-2.0-flash

code snippets

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

—

-0.42

or

-0.42

IconModule

-0.41

Vectors

-0.39

and

-0.36

«

-0.36

asius

-0.36

as

-0.35

<h4>

-0.35

POSITIVE LOGITS

 AssemblyTitle

1.04

LookAnd

0.90

CloseOperation

0.90

__':

0.88

 CreateTagHelper

0.82

fortawesome

0.82

ScopeManager

0.82

ReusableCell

0.79

 okuyayım

0.78

InjectAttribute

0.77

Activations Density 3.376%

conditions in code, specifically comparisons where a value is greater than zero

code snippets

No Comments

No Known Activations