INDEX

Explanations

negative news about crimes, conflicts and governments

oai_token-act-pair · gemini-2.0-flash

of

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

ArrowToggle

-0.82

Бахар

-0.67

mergeFrom

-0.67

PROTOBUF

-0.58

 الرياضيه

-0.57

[]:

-0.57

Autoritní

-0.56

 consultato

-0.56

setContentView

-0.55

RenderAtEndOf

-0.54

POSITIVE LOGITS

 AssemblyCompany

0.67

orghini

0.47

 Andes

0.46

 geweest

0.46

setOnAction

0.45

níků

0.45

nościo

0.45

kozá

0.43

 actionMode

0.43

diga

0.43

Activations Density 2.259%

negative news about crimes, conflicts and governments

of

No Comments

No Known Activations