INDEX

Explanations

C code related to memory access, especially PCI

oai_token-act-pair · gemini-2.0-flash

_

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

 الرياضيه

-0.79

Посилання

-0.71

 jurídica

-0.66

Географи

-0.65

omeness

-0.64

Зноскі

-0.63

Приятного

-0.62

ayangkan

-0.62

Дереккөздер

-0.62

AddTagHelper

-0.61

POSITIVE LOGITS

STR

0.48

cL

0.47

ENOMEM

0.47

ReadInt

0.46

Str

0.45

CR

0.45

Acc

0.45

tC

0.45

Pad

0.44

Ox

0.43

Activations Density 34.480%

C code related to memory access, especially PCI

_

No Comments

No Known Activations