INDEX

Explanations

C++ code related to user input and output

oai_token-act-pair · gemini-2.0-flash

C++ output streams

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

組

-0.49

 Normdatei

-0.49

 createSprite

-0.46

CWE

-0.46

 Grunde

-0.45

ọn

-0.45

__.__

-0.45

 colspan

-0.45

ধ্য

-0.45

 fond

-0.44

POSITIVE LOGITS

 ModelExpression

0.85

 intStringLen

0.56

spesies

0.55

 catholique

0.54

 Socialista

0.54

netje

0.53

 Constitucional

0.52

CodedInputStream

0.52

 chrétienne

0.51

bibinfo

0.51

Activations Density 0.356%

C++ code related to user input and output

C++ output streams

No Comments

No Known Activations