INDEX

Explanations

code blocks, especially those using the keywords "if", "else", and "{"

oai_token-act-pair · gemini-2.0-flash

code

np_max-act-logits · gemini-2.0-flash

New Auto-Interp

Configuration

google/gemma-scope-2b-pt-transcoders/layer_25/width_16k/average_l0_41

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.25.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

-0.56

roën

-0.50

Jîn

-0.46

 Alfaro

-0.45

uginosa

-0.44

epi

-0.44

 Suárez

-0.44

 Marzo

-0.43

 maroca

-0.43

POSITIVE LOGITS

});*/

0.69

tvguidetime

0.68

ंदीखरीदारी

0.67

Filmografie

0.67

[]:

0.64

ⓧ

0.64

сылкі

0.63

''');

0.63

$__

0.62

__((

0.61

Activations Density 5.943%

code blocks, especially those using the keywords "if", "else", and "{"

code

No Comments

No Known Activations

code blocks, especially those using the keywords "if", "else", and "{"

code

No Comments

No Known Activations