INDEX

Explanations

people asking for help or information

oai_token-act-pair · gemini-2.0-flash

foreign words

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

govt

-0.57

 ước

-0.52

 mate

-0.51

inherits

-0.48

 errorCode

-0.47

 Sophia

-0.47

 mates

-0.46

Mate

-0.46

 géné

-0.46

 Mate

-0.46

POSITIVE LOGITS

 مشين

0.99

tagHelperRunner

0.79

 تانيه

0.75

expandindo

0.71

ⓧ

0.66

DoubleQuotes

0.63

 protoimpl

0.63

ThroughAttribute

0.61

EndInit

0.59

principalTable

0.59

Activations Density 9.062%

people asking for help or information

foreign words

No Comments

No Known Activations