INDEX

Explanations

code comments, code documentation, and programming related keywords

oai_token-act-pair · gemini-2.0-flash

code comments

np_max-act · gemini-2.0-flash

New Auto-Interp

Configuration

google/gemma-scope-2b-pt-transcoders/layer_12/width_16k/average_l0_6

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.12.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

Geplaatst

-0.69

 mergeFrom

-0.59

الدراسه

-0.52

 foon

-0.49

 alors

-0.47

Хьажоргаш

-0.46

 themſelves

-0.45

 fontos

-0.44

abestanden

-0.44

 poffe

-0.44

POSITIVE LOGITS

DBNull

0.63

 EconPapers

0.63

interopRequire

0.60

出版年

0.59

ficie

0.58

FromNib

0.57

 mAdapter

0.53

nteral

0.53

ckle

0.52

->__

0.51

Activations Density 0.873%

code comments, code documentation, and programming related keywords

code comments

No Comments

No Known Activations