INDEX

Explanations

programming code and file paths

oai_token-act-pair · gemini-2.0-flash

code and technical files

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

 start

-0.77

 fall

-0.72

 play

-0.71

 hold

-0.71

 stay

-0.71

 break

-0.70

 take

-0.70

 call

-0.68

 treat

-0.67

 drop

-0.66

POSITIVE LOGITS

NS

0.63

mn

0.60

MN

0.59

nc

0.58

ct

0.57

fs

0.57

gs

0.57

cc

0.56

 javax

0.56

IA

0.56

Activations Density 15.586%

programming code and file paths

code and technical files

No Comments

No Known Activations