INDEX

Explanations

what appear to be code snippets, especially from Java, C, Javascript and other languages

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_19/width_16k/average_l0_12

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.19.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

 للمعارف

-0.50

তথ্যসূত্র

-0.45

 femininos

-0.41

 demurrer

-0.41

 RSSSF

-0.41

 digitais

-0.40

 Wiktionnaire

-0.40

 متحده

-0.40

 sexuales

-0.40

 faptul

-0.39

POSITIVE LOGITS

<bos>

0.73

 himo

0.54

TabIndex

0.49

 Laus

0.47

Imp

0.47

ibi

0.47

Fle

0.47

Lup

0.47

Tib

0.46

 sumpay

0.46

Activations Density 9.247%

what appear to be code snippets, especially from Java, C, Javascript and other languages

punctuation

No Comments

No Known Activations