INDEX

Explanations

programming code

np_max-act-logits · gemini-2.0-flash

code snippets

oai_token-act-pair · gemini-2.0-flash

code

np_token-act-pair-logits · gemini-2.0-flash

New Auto-Interp

Configuration

google/gemma-scope-2b-pt-transcoders/layer_16/width_16k/average_l0_10

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.16.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

])));

-0.61

 doucement

-0.52

DriverManager

-0.51

"]}

-0.50

__]

-0.48

frutar

-0.47

ocardium

-0.46

tabular

-0.45

withCredentials

-0.44

Touched

-0.44

POSITIVE LOGITS

verwijspagina

0.65

ponses

0.64

BeginInit

0.59

AndroidJUnit

0.58

StoryboardSegue

0.56

MigrationBuilder

0.55

 &___

0.54

WriteBarrier

0.54

 uſed

0.53

 raiſ

0.52

Activations Density 0.577%

programming code

code snippets

code

No Comments

No Known Activations