INDEX

Explanations

evidence of multiple languages in a single document

oai_token-act-pair · gemini-2.0-flash

punctuation

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

Efq

-1.58

 itſelf

-1.58

 myſelf

-1.57

 Theſe

-1.52

 himſelf

-1.50

 themſelves

-1.48

 Jefus

-1.45

 Monfieur

-1.41

 becauſe

-1.34

 ſeveral

-1.32

POSITIVE LOGITS

0.72

0.63

0.54

0.50

0.45

0.44

0.43

...

0.43

Activations Density 0.383%

evidence of multiple languages in a single document

punctuation

No Comments

No Known Activations