INDEX

Explanations

code snippets containing various keywords related to programming, such as array, list, append, etc.

oai_token-act-pair · gemini-2.0-flash

code and variables

np_max-act-logits · gemini-2.0-flash

New Auto-Interp

Configuration

google/gemma-scope-2b-pt-transcoders/layer_24/width_16k/average_l0_37

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.24.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

 snippetHide

-1.02

 Monfieur

-0.98

sizeCache

-0.90

 تضيفلها

-0.89

featureID

-0.89

oredCriteria

-0.87

 himſelf

-0.87

 myſelf

-0.85

principalColumn

-0.84

 '\\;'

-0.82

POSITIVE LOGITS

 raza

0.34

↵

0.34

 menos

0.33

ttar

0.33

 pré

0.31

phosa

0.31

min

0.30

ins

0.30

 υπο

0.29

Activations Density 3.363%

code snippets containing various keywords related to programming, such as array, list, append, etc.

code and variables

No Comments

No Known Activations